Skip to content

Benchmark

MMLU

Scores are percentages. Higher is better.

Models and systems measured
138
Scores recorded
153
Sources
3
IQ weight
0.00

Score distribution

76.9%
Mean
80.1%
Median
12.2%
Std dev
60.1%
10th percentile
88.8%
90th percentile
36.6%
Min
36.6%92.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.00 for chat models, measured over 133 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#Model or systemScore
1GPT 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim92.5%
2Doubao Seed 1.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim92.3%
3o1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.8%
4GPT-4.5 Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.8%
5O1 Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.8%
6Qwen3 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.90.6%
7Sarvam 105B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.6%
8Claude 3.5 Sonnet· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
90.4%
9GPT 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.2%
10Kimi K2 0905· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.2%
11GPT OSS 120B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90%
12GPT OSS 120Bofficial model card Table 3 · reasoning high · published setting; Table 3 does not further specify tool access · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90%
13LongCat Flash Chat· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.7%
14Kimi K2 Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.5%
15MiMo V2.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.4%
16Qwen3 VL 235B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.88.8%
17Qwen3 VL 32B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.88.7%
18DeepSeek V3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
88.5%
19GPT 4o· Epoch AI Benchmarking Hub data
Values from 2 sources
88.1%
20GPT OSS 120Bofficial model card Table 3 · reasoning medium · published setting; Table 3 does not further specify tool access · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.88%
21Qwen 3 235B A22B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.8%
22qwen3-vl-30bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.87.6%
23GPT-4.1 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.5%
24Grok 2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.5%
25Llama 3.1 405B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
87.3%
26Trinity Large PreviewTrinity technical report · Table 4 · exact reported precision· Reported by Arcee AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.87.2%
27Trinity Large PreviewTrinity-Large-Preview Model Card · rounded to one decimal· Reported by Arcee AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.87.2%
28gemini-1.5-pro-002· Epoch AI Benchmarking Hub data86.9%
29o3 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.9%
30Claude 3 Opus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
86.8%
31GPT-4 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
86.5%
32GPT 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
86.4%
33Qwen3 VL 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.86.4%
34Llama 3.3 70B Instruct· Epoch AI Benchmarking Hub data
Values from 2 sources
86.3%
35Grok 2 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.2%
36Particle 1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.1%
37Llama 3.1 70B Instruct0-shot · chain of thought· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.86%
38gemini-1.5-pro-001· Epoch AI Benchmarking Hub data85.9%
39GPT OSS 120Bofficial model card Table 3 · reasoning low · published setting; Table 3 does not further specify tool access · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.85.9%
40Gemini 1.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.9%
41Nova Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.9%
42longcat-flash-lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.5%
43Llama 4 Maverick· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.5%
44GPT OSS 20b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.3%
45GPT OSS 20bofficial model card Table 3 · reasoning high · published setting; Table 3 does not further specify tool access · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.85.3%
46Qwen2.5 72B Instruct· Epoch AI Benchmarking Hub data85.3%
47O1 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.2%
48Qwen: Qwen3 VL 8B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.85.2%
49Sarvam-30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.1%
50Qwen2.5 72B· Epoch AI Benchmarking Hub data85%

Showing 1–50 of 148 results.

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
MiMo V2 Flash Baseofficial Base table · 5-shot· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.86.7%
Qwen3.5-397B-A17B-BaseQwen3.5 release/model card · base-model table· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.88.6%
Qwen3.7-Plus-BaseQwen3.8-Flash-Next release/model card · base-model table· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90.4%
Qwen3.8-27B-BaseQwen3.8-Flash-Next release/model card · base-model table· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.87.5%
Qwen3.8-Flash-Next-BaseQwen3.8-Flash-Next release/model card · base-model table· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90.4%

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Data by LLM Stats · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.