Listings
All listings: Tokenmix
Every listing for the models on page 3 of 5 of Tokenmix, including each model's other versions and routes. Back to Tokenmix
Sold by Tokenmix
28 listings on this page sold by Tokenmix.
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
- Epoch Capabilities Index
- Epoch Capabilities Index benchmark details
| Model | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value | Yap | Epoch Capabilities Index |
|---|---|---|---|---|---|---|---|---|
GPT-5 Codex πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 127.7From 21 benchmarks. Plenty of data behind it. | β 106Β Β±9staleCoding IQ 106.4, 95% interval 98β115. 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. | β | β | βNot published by the provider | 49.4Fair value (49.4). Costs per task about what its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
Kimi K2.7 Code π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 126.9From 102 benchmarks. Plenty of data behind it. | 105Β Β±9Coding IQ 104.5, 95% interval 96β113. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.9081 | $3.7721 | βNot published by the provider | 43.6Poor value (43.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 62 Β±9Chatty (62 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. | 151.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.1 Flash Lite πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 125.3From 275 benchmarks. Plenty of data behind it. | 97Β Β±10Coding IQ 97.2, 95% interval 88β107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.2425 | $1.455 | βNot published by the provider | 55.5Good value (55.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 48 Β±9Typical (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. | 145Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5 mini πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 124.6From 388 benchmarks. Plenty of data behind it. | 98Β Β±14Coding IQ 98.3, 95% interval 85β112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | β | β | βNot published by the provider | 55.1Good value (55.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 40 Β±9Terse (40 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. | 146Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Grok 4.3 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 124.2From 205 benchmarks. Plenty of data behind it. | 101Β Β±8Coding IQ 101.2, 95% interval 94β109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00 | $6.00 | βNot published by the provider | 39.3Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 48 Β±9Typical (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. | βNot measured |
o4 Mini πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 124.0From 384 benchmarks. Plenty of data behind it. | 101Β Β±14Coding IQ 100.7, 95% interval 87β114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.067 | $4.268 | βNot published by the provider | 56.2Good value (56.2). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 53 Β±16Typical (53 Β±16). Generates about as many tokens as models with similar coding results. Measured at low effort. A fair amount of data behind it. | 145.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5.1 Codex Mini πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 123.8From 24 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.2425 | $1.94 | βNot published by the provider | 62.1Good value (62.1). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Kimi K2 Thinking π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 123.8From 184 benchmarks. Plenty of data behind it. | 100Β Β±6Coding IQ 100.2, 95% interval 94β106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.5294 | $2.1176 | βNot published by the provider | 41.6Poor value (41.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 50 Β±18Typical (50 Β±18). 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. | 145.5Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini Embedding 001 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 123.5From 68 benchmarks. Plenty of data behind it. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
Grok 4.1 Fast πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 122.9From 260 benchmarks. Plenty of data behind it. | 95Β Β±14Coding IQ 95.2, 95% interval 82β109. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.19 | $0.475 | βNot published by the provider | 59.7Good value (59.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 56 Β±9Chatty (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. | βNot measured |
Grok 4.1 Fast πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 122.9From 260 benchmarks. Plenty of data behind it. | 95Β Β±14Coding IQ 95.2, 95% interval 82β109. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.19 | $0.475 | βNot published by the provider | 59.7Good value (59.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 56 Β±9Chatty (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. | βNot measured |
MiniMax M2.5 π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 122.8From 192 benchmarks. Plenty of data behind it. | 100Β Β±6Coding IQ 100.4, 95% interval 94β106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.3243 | $1.2971 | βNot published by the provider | 48.7Fair value (48.7). Costs per task about what its benchmark results predict. Plenty of data behind it. | 64 Β±9Chatty (64 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. | βNot measured |
MiniMax M2.5 π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 122.8From 192 benchmarks. Plenty of data behind it. | 100Β Β±6Coding IQ 100.4, 95% interval 94β106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.6485 | $2.5941 | βNot published by the provider | 48.7Fair value (48.7). Costs per task about what its benchmark results predict. Plenty of data behind it. | 64 Β±9Chatty (64 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. | βNot measured |
Claude Haiku 4.5 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 122.6From 470 benchmarks. Plenty of data behind it. | 95Β Β±6Coding IQ 95.1, 95% interval 90β101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.00 | $5.00 | βNot published by the provider | 35.0Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | 59 Β±10Chatty (59 Β±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 142.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5.3 Chat πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 122.4From 61 benchmarks. A fair amount of data behind it. | βNot enough data yet | β | β | βNot published by the provider | 42.0Poor value (42.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
GPT-5.2 Chat πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 122.3From 74 benchmarks. A fair amount of data behind it. | βNot enough data yet | $1.6975 | $13.58 | βNot published by the provider | 48.3Fair value (48.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
GPT-5 Chat πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 122.3From 74 benchmarks. Plenty of data behind it. | βNot enough data yet | β | β | βNot published by the provider | 44.6Poor value (44.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
MiniMax M2.1 π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 122.3From 97 benchmarks. Plenty of data behind it. | 97Β Β±6Coding IQ 96.5, 95% interval 91β102. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.6485 | $2.5941 | βNot published by the provider | 45.1Poor value (45.1). Costs more per task than its benchmark results predict. Plenty of data behind it. | 59 Β±13Chatty (59 Β±13). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | βNot measured |
GPT-5.1 Chat πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 121.7From 12 benchmarks. A fair amount of data behind it. | βNot enough data yet | $1.2125 | $9.70 | βNot published by the provider | 52.1Fair value (52.1). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Gemini 2.5 Flash πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 121.6From 327 benchmarks. Plenty of data behind it. | 86Β Β±16Coding IQ 85.5, 95% interval 70β102. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.291 | $2.425 | βNot published by the provider | 39.0Poor value (39.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | 57 Β±9Chatty (57 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. | 141.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
120.7From 486 benchmarks. Plenty of data behind it. | 92Β Β±6Coding IQ 92.4, 95% interval 87β98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | β | β | βNot published by the provider | 42.8Poor value (42.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 33 Β±8Terse (33 Β±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 136.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GPT 5.4 Nano πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 120.3From 252 benchmarks. Plenty of data behind it. | 104Β Β±6Coding IQ 103.6, 95% interval 97β110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.194 | $1.2125 | βNot published by the provider | 49.5Fair value (49.5). Costs per task about what its benchmark results predict. Plenty of data behind it. | 47 Β±9Typical (47 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. | 146.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3 Pro Image πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 119.8From 189 benchmarks. A fair amount of data behind it. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
MiniMax M2.7 π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 119.8From 207 benchmarks. Plenty of data behind it. | 98Β Β±12Coding IQ 98.4, 95% interval 87β110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.3243 | $1.2971 | βNot published by the provider | 50.7Fair value (50.7). Costs per task about what its benchmark results predict. Plenty of data behind it. | 61 Β±9Chatty (61 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. | βNot measured |
MiniMax M2.7 π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 119.8From 207 benchmarks. Plenty of data behind it. | 98Β Β±12Coding IQ 98.4, 95% interval 87β110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.6485 | $2.5941 | βNot published by the provider | 50.7Fair value (50.7). Costs per task about what its benchmark results predict. Plenty of data behind it. | 61 Β±9Chatty (61 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. | βNot measured |
Codex Mini πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | β 119From 9 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $1.455 | $5.82 | βNot published by the provider | 39.7Poor value (39.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
GPT Image 1.5 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 118.3From 56 benchmarks. A fair amount of data behind it. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
GPT OSS 120B πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 118.2From 424 benchmarks. Plenty of data behind it. | 86Β Β±5Coding IQ 85.5, 95% interval 80β91. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.1455 | $0.582 | βNot published by the provider | 58.4Good value (58.4). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 37 Β±11Terse (37 Β±11). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 140.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)