Skip to content

Listings

All listings: xAI

Every listing for the models on page 1 of 2 of xAI, including each model's other versions and routes. Back to xAI

Sold by xAI

61 listings on this page sold by xAI.

Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
Modelllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValueYapEpoch Capabilities Index
Grok 4.6
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
138.0
From 220 benchmarks. Plenty of data behind it.
120Β Β±11
Coding IQ 120.1, 95% interval 109–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00>200k $4.00cache read $0.50$6.00>200k $12.00500K
56.0
Good value (56.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
47 Β±10
Typical (47 Β±10). Generates about as many tokens as models with similar coding results. Measured at high effort. A fair amount of data behind it.
157.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.7
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
137.7
From 249 benchmarks. Plenty of data behind it.
117Β Β±7
Coding IQ 117.4, 95% interval 111–124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00>200k $4.00cache read $0.50batch $1.60$6.00>200k $12.00batch $4.80500K
41.2
Poor value (41.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
55 Β±14
Typical (55 Β±14). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
156.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.5
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
136.6
From 312 benchmarks. Plenty of data behind it.
117Β Β±8
Coding IQ 117.4, 95% interval 109–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00>200k $4.00cache read $0.50$6.00>200k $12.00500K
56.9
Good value (56.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 Β±9
Terse (37 Β±9). Generates fewer tokens than models with similar coding results. Measured at high effort. A fair amount of data behind it.
155
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.5
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.5-latest Β· latest
136.6
From 312 benchmarks. Plenty of data behind it.
117Β Β±8
Coding IQ 117.4, 95% interval 109–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00>200k $4.00cache read $0.30$6.00>200k $12.00500K
56.9
Good value (56.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 Β±9
Terse (37 Β±9). Generates fewer tokens than models with similar coding results. Measured at high effort. A fair amount of data behind it.
155
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20 Multi-Agent
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
β‰ˆ 130
From 73 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$2.00>200k $2.50cache read $0.20batch $1.00$6.00>200k $5.00batch $2.001MNot enough data yetNot measuredNot measured
Grok 4.20 Multi-Agent
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-multi-agent-0309 Β· 0309
β‰ˆ 130
From 73 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$1.25>200k $2.50cache read $0.20batch $1.00$2.50>200k $5.00batch $2.001MNot enough data yetNot measuredNot measured
Grok 4.20 Multi-Agent
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-multi-agent-beta-0309 Β· beta+0309
β‰ˆ 130
From 73 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$1.25>200k $2.50cache read $0.20$2.50>200k $5.001MNot enough data yetNot measuredNot measured
Grok 4.20 Multi-Agent
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-multi-agent-beta-latest Β· beta+latest
β‰ˆ 130
From 73 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$1.25>200k $2.50cache read $0.20$2.50>200k $5.001MNot enough data yetNot measuredNot measured
Grok 4.20 Multi-Agent
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-multi-agent-latest Β· latest
β‰ˆ 130
From 73 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$1.25>200k $2.50cache read $0.20batch $1.00$2.50>200k $5.00batch $2.001MNot enough data yetNot measuredNot measured
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20batch $1.00$2.50>200k $5.00batch $2.001M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-0309 Β· 0309
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20batch $1.00$2.50>200k $5.00batch $2.001M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-beta Β· beta
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20$2.50>200k $5.001M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-beta-0309 Β· beta+0309
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20$2.50>200k $5.001M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-beta-latest Β· beta+latest
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20$2.50>200k $5.001M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-beta-latest-non-reasoning Β· beta+latest+non-reasoning
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20$2.50>200k $5.001M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-beta-latest-reasoning Β· beta+latest+reasoning
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20$2.50>200k $5.001M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-beta-non-reasoning Β· beta+non-reasoning
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20$2.50>200k $5.001M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-beta-0309-non-reasoning Β· beta+non-reasoning+0309
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20$2.50>200k $5.001M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-beta-reasoning Β· beta+reasoning
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20$2.50>200k $5.001M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-beta-0309-reasoning Β· beta+reasoning+0309
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20$2.50>200k $5.001M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-non-reasoning-latest Β· latest+non-reasoning
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20batch $1.00$2.50>200k $5.00batch $2.001M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-reasoning-latest Β· latest+reasoning
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20batch $1.00$2.50>200k $5.00batch $2.001M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-non-reasoning Β· non-reasoning
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20batch $1.00$2.50>200k $5.00batch $2.001M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-0309-non-reasoning Β· non-reasoning+0309
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20batch $1.00$2.50>200k $5.00batch $2.001M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-reasoning Β· reasoning
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20batch $1.00$2.50>200k $5.00batch $2.001M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-0309-reasoning Β· reasoning+0309
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20batch $1.00$2.50>200k $5.00batch $2.001M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok Build 0.1
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
128.7
From 32 benchmarks. A fair amount of data behind it.
β‰ˆ 110Β Β±23
Coding IQ 109.5, 95% interval 87–133. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00>200k $2.00cache read $0.20$2.00>200k $4.00256K
57.8
Good value (57.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Grok 4
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
grok-4-0709 Β· 0709
125.2
From 296 benchmarks. Plenty of data behind it.
98Β Β±13
Coding IQ 98.0, 95% interval 85–111. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00cache read $0.75$15.00256K
32.7
Poor value (32.7). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
146.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
125.2
From 296 benchmarks. Plenty of data behind it.
98Β Β±13
Coding IQ 98.0, 95% interval 85–111. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00$15.00Not published by the provider
32.7
Poor value (32.7). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
146.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.3
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
124.2
From 205 benchmarks. Plenty of data behind it.
101Β Β±8
Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20batch $1.00$2.50>200k $5.00batch $2.001M
39.3
Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
48 Β±9
Typical (48 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok 4.3
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.3-latest Β· latest
124.2
From 205 benchmarks. Plenty of data behind it.
101Β Β±8
Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20batch $1.00$2.50>200k $5.00batch $2.001M
39.3
Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
48 Β±9
Typical (48 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok 4.1 Fast
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGrok 4.2 FastWe compared the version names in our catalogue.
grok-4-1-fast-non-reasoning Β· non-reasoning
122.9
From 260 benchmarks. Plenty of data behind it.
95Β Β±14
Coding IQ 95.2, 95% interval 82–109. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20cache read $0.05$0.502M
59.7
Good value (59.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
56 Β±9
Chatty (56 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok 4.1 Fast
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGrok 4.2 FastWe compared the version names in our catalogue.
grok-4-1-fast-reasoning Β· reasoning
122.9
From 260 benchmarks. Plenty of data behind it.
95Β Β±14
Coding IQ 95.2, 95% interval 82–109. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20cache read $0.05$0.502M
59.7
Good value (59.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
56 Β±9
Chatty (56 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok 4 Fast
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGrok 4.2 FastWe compared the version names in our catalogue.
grok-4-fast-non-reasoning Β· non-reasoning
122.2
From 239 benchmarks. Plenty of data behind it.
91Β Β±16
Coding IQ 91.0, 95% interval 75–107. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20cache read $0.05$0.502M
65.9
Good value (65.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measured
144.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4 Fast
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGrok 4.2 FastWe compared the version names in our catalogue.
grok-4-fast-reasoning Β· reasoning
122.2
From 239 benchmarks. Plenty of data behind it.
91Β Β±16
Coding IQ 91.0, 95% interval 75–107. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20cache read $0.05$0.502M
65.9
Good value (65.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measured
144.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4 Fast
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGrok 4.2 FastWe compared the version names in our catalogue.
122.2
From 239 benchmarks. Plenty of data behind it.
91Β Β±16
Coding IQ 91.0, 95% interval 75–107. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20$0.50Not published by the provider
65.9
Good value (65.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measured
144.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 3 Mini
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
120.4
From 190 benchmarks. Plenty of data behind it.
β‰ˆ 95Β Β±12
Coding IQ 94.5, 95% interval 82–107. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.30cache read $0.075$0.50131K
50.6
Fair value (50.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
Not measured
139.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok Imagine Image 2.0
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
120.0
From 17 benchmarks. A fair amount of data behind it.
Not enough data yetβ€”β€”Not published by the providerNot enough data yetNot measuredNot measured
Grok Imagine Image 2.0
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
low+1024-x-1024
120.0
From 17 benchmarks. A fair amount of data behind it.
Not enough data yetβ€”β€”Not published by the providerNot enough data yetNot measuredNot measured
Grok Code Fast 1
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
118.4
From 31 benchmarks. Plenty of data behind it.
89Β Β±8
Coding IQ 88.7, 95% interval 81–96. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20>200k $2.00cache read $0.02$1.50>200k $4.00256K
52.1
Fair value (52.1). Costs per task about what its benchmark results predict. A fair amount of data behind it.
43 Β±9
Terse (43 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok Code Fast 1
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-code-fast-1-0825 Β· 0825
118.4
From 31 benchmarks. Plenty of data behind it.
89Β Β±8
Coding IQ 88.7, 95% interval 81–96. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00>200k $2.00cache read $0.20$2.00>200k $4.00256K
52.1
Fair value (52.1). Costs per task about what its benchmark results predict. A fair amount of data behind it.
43 Β±9
Terse (43 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok 3
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
118.2
From 188 benchmarks. Plenty of data behind it.
β‰ˆ 91Β Β±10stale
Coding IQ 90.7, 95% interval 80–101. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. Its newest result is over a year old.
$3.00cache read $0.75$15.00131K
34.0
Poor value (34.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
137.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 3
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
grok-3-fast Β· fast
118.2
From 188 benchmarks. Plenty of data behind it.
β‰ˆ 91Β Β±10stale
Coding IQ 90.7, 95% interval 80–101. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. Its newest result is over a year old.
$5.00cache read $1.25$25.00131K
34.0
Poor value (34.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
137.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 2
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
grok-2-1212 Β· 1212
112.6
From 78 benchmarks. Plenty of data behind it.
β‰ˆ 83Β Β±10
Coding IQ 83.1, 95% interval 73–93. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00$10.0033K
25.9
Poor value (25.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
129.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok Imagine Video
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
β‰ˆ 112
From 7 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yetβ€”β€”1KNot enough data yetNot measuredNot measured
Grok Beta
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
107.2
From 11 benchmarks. A fair amount of data behind it.
β‰ˆ 78Β Β±11stale
Coding IQ 77.6, 95% interval 66–89. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. Its newest result is over a year old.
$5.00$15.00Not published by the providerNot enough data yetNot measuredNot measured
Grok Imagine Image
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
β‰ˆ 104
From 13 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yetβ€”β€”16KNot enough data yetNot measuredNot measured
Grok Imagine Image
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-imagine-image-2026-03-02 Β· 2026-03-02
β‰ˆ 104
From 13 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yetβ€”β€”Not published by the providerNot enough data yetNot measuredNot measured
Grok 2 Vision 1212
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
1212
96.5
From 34 benchmarks. Plenty of data behind it.
Not enough data yet$2.00$10.0033K
31.4
Poor value (31.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Grok 3 Mini Fast Beta
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
grok-3-mini-fast
Not enough data yetNot enough data yet$0.60cache read $0.15$4.00131K
72.4
Good value (72.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
Grok Code Fast
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$1.00>200k $2.00cache read $0.20$2.00>200k $4.00256KNot enough data yetNot measuredNot measured
grok-4.20-experimental-beta
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-experimental-beta-0304 Β· 0304
Not enough data yetNot enough data yet$1.25>200k $2.50cache read $0.20$2.50>200k $5.001MNot enough data yetNot measuredNot measured
grok-4.20-experimental-beta
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-experimental-beta-latest Β· latest
Not enough data yetNot enough data yet$1.25>200k $2.50cache read $0.20$2.50>200k $5.001MNot enough data yetNot measuredNot measured
grok-4.20-experimental-beta
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-experimental-beta-non-reasoning-latest Β· latest+non-reasoning
Not enough data yetNot enough data yet$1.25>200k $2.50cache read $0.20$2.50>200k $5.001MNot enough data yetNot measuredNot measured
grok-4.20-experimental-beta
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-experimental-beta-reasoning-latest Β· latest+reasoning
Not enough data yetNot enough data yet$1.25>200k $2.50cache read $0.20$2.50>200k $5.001MNot enough data yetNot measuredNot measured
grok-4.20-experimental-beta
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-experimental-beta-0304-non-reasoning Β· non-reasoning+0304
Not enough data yetNot enough data yet$1.25>200k $2.50cache read $0.20$2.50>200k $5.001MNot enough data yetNot measuredNot measured
grok-4.20-experimental-beta
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-experimental-beta-0304-reasoning Β· reasoning+0304
Not enough data yetNot enough data yet$1.25>200k $2.50cache read $0.20$2.50>200k $5.001MNot enough data yetNot measuredNot measured
grok-4.20-multi-agent-experimental-beta
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-multi-agent-experimental-beta-0304 Β· 0304
Not enough data yetNot enough data yet$1.25>200k $2.50cache read $0.20$2.50>200k $5.001MNot enough data yetNot measuredNot measured
grok-4.20-multi-agent-experimental-beta
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-multi-agent-experimental-beta-latest Β· latest
Not enough data yetNot enough data yet$1.25>200k $2.50cache read $0.20$2.50>200k $5.001MNot enough data yetNot measuredNot measured
grok-4.20-non-reasoning-gv2
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$1.25>200k $2.50cache read $0.20$2.50>200k $5.001MNot enough data yetNot measuredNot measured
grok-4.20-reasoning-gv2
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$1.25>200k $2.50cache read $0.20$2.50>200k $5.001MNot enough data yetNot measuredNot measured

Run by xAI

69 listings on this page where xAI runs the model. Another provider sells these listings.

Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
ModelProviderllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValueYapEpoch Capabilities Index
Grok 4.6
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Eden AI
138.0
From 220 benchmarks. Plenty of data behind it.
120Β Β±11
Coding IQ 120.1, 95% interval 109–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50$6.00500K
56.0
Good value (56.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
47 Β±10
Typical (47 Β±10). Generates about as many tokens as models with similar coding results. Measured at high effort. A fair amount of data behind it.
157.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.6
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Llmgateway
138.0
From 220 benchmarks. Plenty of data behind it.
120Β Β±11
Coding IQ 120.1, 95% interval 109–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50$6.00Not published by the provider
56.0
Good value (56.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
47 Β±10
Typical (47 Β±10). Generates about as many tokens as models with similar coding results. Measured at high effort. A fair amount of data behind it.
157.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.6
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
πŸ‡ΊπŸ‡Έ US
Β NanoGPT
138.0
From 220 benchmarks. Plenty of data behind it.
120Β Β±11
Coding IQ 120.1, 95% interval 109–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.10cache read $0.525$6.30Not published by the provider
56.0
Good value (56.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
47 Β±10
Typical (47 Β±10). Generates about as many tokens as models with similar coding results. Measured at high effort. A fair amount of data behind it.
157.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.6
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β OpenRouter
138.0
From 220 benchmarks. Plenty of data behind it.
120Β Β±11
Coding IQ 120.1, 95% interval 109–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50$6.00500K
56.0
Good value (56.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
47 Β±10
Typical (47 Β±10). Generates about as many tokens as models with similar coding results. Measured at high effort. A fair amount of data behind it.
157.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.6
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
x-ai/grok-4.6:batch Β· batch
Β OpenRouter
138.0
From 220 benchmarks. Plenty of data behind it.
120Β Β±11
Coding IQ 120.1, 95% interval 109–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.60cache read $0.40$4.80500K
56.0
Good value (56.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
47 Β±10
Typical (47 Β±10). Generates about as many tokens as models with similar coding results. Measured at high effort. A fair amount of data behind it.
157.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.6
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
priority
Β OpenRouter
138.0
From 220 benchmarks. Plenty of data behind it.
120Β Β±11
Coding IQ 120.1, 95% interval 109–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00cache read $1.00$12.00500K
56.0
Good value (56.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
47 Β±10
Typical (47 Β±10). Generates about as many tokens as models with similar coding results. Measured at high effort. A fair amount of data behind it.
157.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.6
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
zdr
Β OpenRouter
138.0
From 220 benchmarks. Plenty of data behind it.
120Β Β±11
Coding IQ 120.1, 95% interval 109–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50$6.00500K
56.0
Good value (56.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
47 Β±10
Typical (47 Β±10). Generates about as many tokens as models with similar coding results. Measured at high effort. A fair amount of data behind it.
157.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.6
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
zdr/priority
Β OpenRouter
138.0
From 220 benchmarks. Plenty of data behind it.
120Β Β±11
Coding IQ 120.1, 95% interval 109–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00cache read $1.00$12.00500K
56.0
Good value (56.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
47 Β±10
Typical (47 Β±10). Generates about as many tokens as models with similar coding results. Measured at high effort. A fair amount of data behind it.
157.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.6
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Requesty
138.0
From 220 benchmarks. Plenty of data behind it.
120Β Β±11
Coding IQ 120.1, 95% interval 109–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00>200k $4.00cache read $0.50$6.00>200k $12.00cache write $2.00500K
56.0
Good value (56.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
47 Β±10
Typical (47 Β±10). Generates about as many tokens as models with similar coding results. Measured at high effort. A fair amount of data behind it.
157.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.7
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Eden AI
137.7
From 249 benchmarks. Plenty of data behind it.
117Β Β±7
Coding IQ 117.4, 95% interval 111–124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50$6.00500K
41.2
Poor value (41.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
55 Β±14
Typical (55 Β±14). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
156.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.7
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Llmgateway
137.7
From 249 benchmarks. Plenty of data behind it.
117Β Β±7
Coding IQ 117.4, 95% interval 111–124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50$6.00Not published by the provider
41.2
Poor value (41.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
55 Β±14
Typical (55 Β±14). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
156.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.7
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
πŸ‡ΊπŸ‡Έ US
Β NanoGPT
137.7
From 249 benchmarks. Plenty of data behind it.
117Β Β±7
Coding IQ 117.4, 95% interval 111–124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.10cache read $0.525$6.30Not published by the provider
41.2
Poor value (41.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
55 Β±14
Typical (55 Β±14). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
156.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.7
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β OpenRouter
137.7
From 249 benchmarks. Plenty of data behind it.
117Β Β±7
Coding IQ 117.4, 95% interval 111–124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50$6.00500K
41.2
Poor value (41.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
55 Β±14
Typical (55 Β±14). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
156.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.7
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
x-ai/grok-4.7:batch Β· batch
Β OpenRouter
137.7
From 249 benchmarks. Plenty of data behind it.
117Β Β±7
Coding IQ 117.4, 95% interval 111–124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.60cache read $0.40$4.80500K
41.2
Poor value (41.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
55 Β±14
Typical (55 Β±14). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
156.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.7
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
priority
Β OpenRouter
137.7
From 249 benchmarks. Plenty of data behind it.
117Β Β±7
Coding IQ 117.4, 95% interval 111–124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00cache read $1.00$12.00500K
41.2
Poor value (41.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
55 Β±14
Typical (55 Β±14). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
156.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.7
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
zdr
Β OpenRouter
137.7
From 249 benchmarks. Plenty of data behind it.
117Β Β±7
Coding IQ 117.4, 95% interval 111–124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50$6.00500K
41.2
Poor value (41.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
55 Β±14
Typical (55 Β±14). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
156.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.7
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
zdr/priority
Β OpenRouter
137.7
From 249 benchmarks. Plenty of data behind it.
117Β Β±7
Coding IQ 117.4, 95% interval 111–124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00cache read $1.00$12.00500K
41.2
Poor value (41.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
55 Β±14
Typical (55 Β±14). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
156.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.5
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Eden AI
136.6
From 312 benchmarks. Plenty of data behind it.
117Β Β±8
Coding IQ 117.4, 95% interval 109–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.30$6.00500K
56.9
Good value (56.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 Β±9
Terse (37 Β±9). Generates fewer tokens than models with similar coding results. Measured at high effort. A fair amount of data behind it.
155
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.5
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Llmgateway
136.6
From 312 benchmarks. Plenty of data behind it.
117Β Β±8
Coding IQ 117.4, 95% interval 109–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.30$6.00Not published by the provider
56.9
Good value (56.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 Β±9
Terse (37 Β±9). Generates fewer tokens than models with similar coding results. Measured at high effort. A fair amount of data behind it.
155
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.5
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
πŸ‡ΊπŸ‡Έ US
Β NanoGPT
136.6
From 312 benchmarks. Plenty of data behind it.
117Β Β±8
Coding IQ 117.4, 95% interval 109–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.10cache read $0.315$6.30Not published by the provider
56.9
Good value (56.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 Β±9
Terse (37 Β±9). Generates fewer tokens than models with similar coding results. Measured at high effort. A fair amount of data behind it.
155
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.5
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β OpenRouter
136.6
From 312 benchmarks. Plenty of data behind it.
117Β Β±8
Coding IQ 117.4, 95% interval 109–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.30$6.00500K
56.9
Good value (56.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 Β±9
Terse (37 Β±9). Generates fewer tokens than models with similar coding results. Measured at high effort. A fair amount of data behind it.
155
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.5
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
priority
Β OpenRouter
136.6
From 312 benchmarks. Plenty of data behind it.
117Β Β±8
Coding IQ 117.4, 95% interval 109–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00cache read $0.60$12.00500K
56.9
Good value (56.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 Β±9
Terse (37 Β±9). Generates fewer tokens than models with similar coding results. Measured at high effort. A fair amount of data behind it.
155
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.5
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
zdr
Β OpenRouter
136.6
From 312 benchmarks. Plenty of data behind it.
117Β Β±8
Coding IQ 117.4, 95% interval 109–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.30$6.00500K
56.9
Good value (56.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 Β±9
Terse (37 Β±9). Generates fewer tokens than models with similar coding results. Measured at high effort. A fair amount of data behind it.
155
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.5
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
zdr/priority
Β OpenRouter
136.6
From 312 benchmarks. Plenty of data behind it.
117Β Β±8
Coding IQ 117.4, 95% interval 109–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00cache read $0.60$12.00500K
56.9
Good value (56.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 Β±9
Terse (37 Β±9). Generates fewer tokens than models with similar coding results. Measured at high effort. A fair amount of data behind it.
155
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.5
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Requesty
136.6
From 312 benchmarks. Plenty of data behind it.
117Β Β±8
Coding IQ 117.4, 95% interval 109–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00>200k $4.00cache read $0.50$6.00>200k $12.00cache write $2.00500K
56.9
Good value (56.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 Β±9
Terse (37 Β±9). Generates fewer tokens than models with similar coding results. Measured at high effort. A fair amount of data behind it.
155
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20 Multi-Agent
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
πŸ‡ΊπŸ‡Έ US
Β NanoGPT
β‰ˆ 130
From 73 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$1.3125cache read $0.21$2.625Not published by the providerNot enough data yetNot measuredNot measured
Grok 4.20 Multi-Agent
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β OpenRouter
β‰ˆ 130
From 73 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$1.25cache read $0.20$2.502MNot enough data yetNot measuredNot measured
Grok 4.20 Multi-Agent
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
priority
Β OpenRouter
β‰ˆ 130
From 73 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$2.50cache read $0.40$5.002MNot enough data yetNot measuredNot measured
Grok 4.20 Multi-Agent
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
zdr
Β OpenRouter
β‰ˆ 130
From 73 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$1.25cache read $0.20$2.502MNot enough data yetNot measuredNot measured
Grok 4.20 Multi-Agent
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
zdr/priority
Β OpenRouter
β‰ˆ 130
From 73 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$2.50cache read $0.40$5.002MNot enough data yetNot measuredNot measured
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-0309-non-reasoning Β· non-reasoning+0309
Β Eden AI
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.20$2.501M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-4.20-0309-reasoning Β· reasoning+0309
Β Eden AI
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.20$2.501M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
grok-4.20-beta-0309-non-reasoning Β· beta+non-reasoning+0309
Β Llmgateway
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$6.00Not published by the provider
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
grok-4.20-beta-0309-reasoning Β· beta+reasoning+0309
Β Llmgateway
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$6.00Not published by the provider
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
πŸ‡ΊπŸ‡Έ US
Β NanoGPT
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.3125cache read $0.21$2.625Not published by the provider
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β OpenRouter
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.20$2.502M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
priority
Β OpenRouter
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50cache read $0.40$5.002M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
zdr
Β OpenRouter
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.20$2.502M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
zdr/priority
Β OpenRouter
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50cache read $0.40$5.002M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok Build 0.1
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Llmgateway
128.7
From 32 benchmarks. A fair amount of data behind it.
β‰ˆ 110Β Β±23
Coding IQ 109.5, 95% interval 87–133. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.20$2.00Not published by the provider
57.8
Good value (57.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Grok Build 0.1
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Requesty
128.7
From 32 benchmarks. A fair amount of data behind it.
β‰ˆ 110Β Β±23
Coding IQ 109.5, 95% interval 87–133. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.10$2.00256K
57.8
Good value (57.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Grok 4
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Llmgateway
125.2
From 296 benchmarks. Plenty of data behind it.
98Β Β±13
Coding IQ 98.0, 95% interval 85–111. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00cache read $0.75$15.00Not published by the provider
32.7
Poor value (32.7). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
146.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Requesty
125.2
From 296 benchmarks. Plenty of data behind it.
98Β Β±13
Coding IQ 98.0, 95% interval 85–111. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00>128k $6.00cache read $0.75$15.00>128k $30.00cache write $3.00256K
32.7
Poor value (32.7). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
146.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.3
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Eden AI
124.2
From 205 benchmarks. Plenty of data behind it.
101Β Β±8
Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.20$2.501M
39.3
Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
48 Β±9
Typical (48 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok 4.3
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Llmgateway
124.2
From 205 benchmarks. Plenty of data behind it.
101Β Β±8
Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.20$2.50Not published by the provider
39.3
Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
48 Β±9
Typical (48 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok 4.3
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
πŸ‡ΊπŸ‡Έ US
Β NanoGPT
124.2
From 205 benchmarks. Plenty of data behind it.
101Β Β±8
Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.3125cache read $0.21$2.625Not published by the provider
39.3
Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
48 Β±9
Typical (48 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok 4.3
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β OpenRouter
124.2
From 205 benchmarks. Plenty of data behind it.
101Β Β±8
Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.20$2.501M
39.3
Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
48 Β±9
Typical (48 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok 4.3
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
x-ai/grok-4.3:batch Β· batch
Β OpenRouter
124.2
From 205 benchmarks. Plenty of data behind it.
101Β Β±8
Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.16$2.001M
39.3
Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
48 Β±9
Typical (48 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok 4.3
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
priority
Β OpenRouter
124.2
From 205 benchmarks. Plenty of data behind it.
101Β Β±8
Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50cache read $0.40$5.001M
39.3
Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
48 Β±9
Typical (48 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok 4.3
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
zdr
Β OpenRouter
124.2
From 205 benchmarks. Plenty of data behind it.
101Β Β±8
Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.20$2.501M
39.3
Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
48 Β±9
Typical (48 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok 4.3
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
zdr/priority
Β OpenRouter
124.2
From 205 benchmarks. Plenty of data behind it.
101Β Β±8
Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50cache read $0.40$5.001M
39.3
Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
48 Β±9
Typical (48 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok 4.3
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Requesty
124.2
From 205 benchmarks. Plenty of data behind it.
101Β Β±8
Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25>200k $2.50cache read $0.20$2.50>200k $5.00cache write $1.251M
39.3
Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
48 Β±9
Typical (48 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok 4.1 Fast
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGrok 4.2 FastWe compared the version names in our catalogue.
grok-4-1-fast-reasoning Β· reasoning
Β Llmgateway
122.9
From 260 benchmarks. Plenty of data behind it.
95Β Β±14
Coding IQ 95.2, 95% interval 82–109. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20cache read $0.05$0.50Not published by the provider
59.7
Good value (59.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
56 Β±9
Chatty (56 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok 4.1 Fast
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGrok 4.2 FastWe compared the version names in our catalogue.
xai/grok-4-1-fast-non-reasoning Β· non-reasoning
Β Requesty
122.9
From 260 benchmarks. Plenty of data behind it.
95Β Β±14
Coding IQ 95.2, 95% interval 82–109. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20>128k $0.40cache read $0.05$0.50>128k $1.00cache write $0.202M
59.7
Good value (59.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
56 Β±9
Chatty (56 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok 4.1 Fast
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGrok 4.2 FastWe compared the version names in our catalogue.
xai/grok-4-1-fast-reasoning Β· reasoning
Β Requesty
122.9
From 260 benchmarks. Plenty of data behind it.
95Β Β±14
Coding IQ 95.2, 95% interval 82–109. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20>128k $0.40cache read $0.05$0.50>128k $1.00cache write $0.202M
59.7
Good value (59.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
56 Β±9
Chatty (56 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok 4 Fast
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGrok 4.2 FastWe compared the version names in our catalogue.
xai/grok-4-fast-non-reasoning Β· non-reasoning
Β Eden AI
122.2
From 239 benchmarks. Plenty of data behind it.
91Β Β±16
Coding IQ 91.0, 95% interval 75–107. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20cache read $0.05$0.502M
65.9
Good value (65.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measured
144.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4 Fast
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGrok 4.2 FastWe compared the version names in our catalogue.
Β Requesty
122.2
From 239 benchmarks. Plenty of data behind it.
91Β Β±16
Coding IQ 91.0, 95% interval 75–107. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20>128k $0.40cache read $0.05$0.50>128k $1.00cache write $0.202M
65.9
Good value (65.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measured
144.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4 Fast
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGrok 4.2 FastWe compared the version names in our catalogue.
xai/grok-4-fast-non-reasoning Β· non-reasoning
Β Requesty
122.2
From 239 benchmarks. Plenty of data behind it.
91Β Β±16
Coding IQ 91.0, 95% interval 75–107. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20>128k $0.40cache read $0.05$0.50>128k $1.00cache write $0.202M
65.9
Good value (65.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measured
144.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 3 Mini
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Requesty
120.4
From 190 benchmarks. Plenty of data behind it.
β‰ˆ 95Β Β±12
Coding IQ 94.5, 95% interval 82–107. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.30$0.50131K
50.6
Fair value (50.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
Not measured
139.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 3 Mini
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-3-mini:high Β· high
Β Requesty
120.4
From 190 benchmarks. Plenty of data behind it.
β‰ˆ 95Β Β±12
Coding IQ 94.5, 95% interval 82–107. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.30$0.50131K
50.6
Fair value (50.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
Not measured
139.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 3 Mini
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai/grok-3-mini:low Β· low
Β Requesty
120.4
From 190 benchmarks. Plenty of data behind it.
β‰ˆ 95Β Β±12
Coding IQ 94.5, 95% interval 82–107. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.30$0.50131K
50.6
Fair value (50.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
Not measured
139.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok Imagine Image 2.0
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Llmgateway
120.0
From 17 benchmarks. A fair amount of data behind it.
Not enough data yetβ€”β€”Not published by the providerNot enough data yetNot measuredNot measured
Grok Imagine Image 2.0
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
image-low-1k
Β Llmgateway
120.0
From 17 benchmarks. A fair amount of data behind it.
Not enough data yetβ€”β€”Not published by the providerNot enough data yetNot measuredNot measured
Grok Imagine Image 2.0
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
image-low-2k
Β Llmgateway
120.0
From 17 benchmarks. A fair amount of data behind it.
Not enough data yetβ€”β€”Not published by the providerNot enough data yetNot measuredNot measured
Grok Imagine Image 2.0
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
image-medium-1k
Β Llmgateway
120.0
From 17 benchmarks. A fair amount of data behind it.
Not enough data yetβ€”β€”Not published by the providerNot enough data yetNot measuredNot measured
Grok Imagine Image 2.0
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
image-medium-2k
Β Llmgateway
120.0
From 17 benchmarks. A fair amount of data behind it.
Not enough data yetβ€”β€”Not published by the providerNot enough data yetNot measuredNot measured
Grok Code Fast 1
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Requesty
118.4
From 31 benchmarks. Plenty of data behind it.
89Β Β±8
Coding IQ 88.7, 95% interval 81–96. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20cache read $0.02$1.50256K
52.1
Fair value (52.1). Costs per task about what its benchmark results predict. A fair amount of data behind it.
43 Β±9
Terse (43 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok 3
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Requesty
118.2
From 188 benchmarks. Plenty of data behind it.
β‰ˆ 91Β Β±10stale
Coding IQ 90.7, 95% interval 80–101. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. Its newest result is over a year old.
$5.00$25.00131K
34.0
Poor value (34.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
137.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok Imagine Image
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Β Llmgateway
β‰ˆ 104
From 13 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yetβ€”β€”Not published by the providerNot enough data yetNot measuredNot measured

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)

How this data works