Skip to content
Models and systems measured
182
Scores recorded
185
Sources
4
IQ weight
1.41

Score distribution

38.2%
Mean
35.8%
Median
23.1%
Std dev
7.9%
10th percentile
78.2%
90th percentile
2.9%
Min
2.9%91%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.41 for chat models, measured over 176 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
51Meta Llama 3 70b· Hugging Face Open LLM Leaderboard data48.7%
52l3-70b-euryale-v2.1· Hugging Face Open LLM Leaderboard data48.7%
53WizardLM 2 8x22B· Hugging Face Open LLM Leaderboard data48.6%
54Qwen 2.5 Coder 32B· Hugging Face Open LLM Leaderboard data48.5%
55dolphin-2-9-2-qwen2-72b· Hugging Face Open LLM Leaderboard data47.7%
56Llama 3.1 Nemotron 70B Instruct HF· Hugging Face Open LLM Leaderboard data47.1%
57Llama 2 13b· Epoch AI Benchmarking Hub data47%
58Llama 3.1 70B· Hugging Face Open LLM Leaderboard data46.4%
59mixtral-8x22b-v0.1· Hugging Face Open LLM Leaderboard data45.6%
60Qwen2.5 14B· Hugging Face Open LLM Leaderboard data45.1%
61Qwen1.5-110B-Chat· Hugging Face Open LLM Leaderboard data45%
62Qwen1.5-32B-Chat· Hugging Face Open LLM Leaderboard data44.6%
63Yi 1.5 34B Chat16k· Hugging Face Open LLM Leaderboard data44.5%
64Yi 1.5 34B Chat· Hugging Face Open LLM Leaderboard data44.3%
65qwen2.5-coder-14b-instruct· Hugging Face Open LLM Leaderboard data44.2%
66Mixtral 8x22B Instruct v0.1· Hugging Face Open LLM Leaderboard data44.1%
67Yi-6B· Epoch AI Benchmarking Hub data
Values from 2 sources
42.8%
68Gemma 2 9B IT· Hugging Face Open LLM Leaderboard data42.1%
69Qwen2 57B A14B Instruct· Hugging Face Open LLM Leaderboard data41.8%
70DeepSeek R1 Distill Qwen 14B· Hugging Face Open LLM Leaderboard data40.7%
71qwen2p5-coder-14b· Hugging Face Open LLM Leaderboard data40.5%
72Llama 2 7b· Epoch AI Benchmarking Hub data39.2%
73Phi 4 Mini· Hugging Face Open LLM Leaderboard data38.7%
74Aya Expanse 32B· Hugging Face Open LLM Leaderboard data38.7%
75LLaMA 13B· Epoch AI Benchmarking Hub data37.9%
76Llama 3 70b Instruct Abliterated v3.5· Hugging Face Open LLM Leaderboard data37.9%
77Qwen2 7B Instruct· Hugging Face Open LLM Leaderboard data37.8%
78gemma2-27b· Hugging Face Open LLM Leaderboard data37.4%
79Nous Hermes 2 Mixtral 8x7B DPO· Hugging Face Open LLM Leaderboard data37.1%
80Phi-3 Mini 128K Instruct· Hugging Face Open LLM Leaderboard data37.1%
81C4AI Command R7b 12 2024· Hugging Face Open LLM Leaderboard data36%
82Yi-34B200k· Hugging Face Open LLM Leaderboard data36%
83DBRX-instruct· Hugging Face Open LLM Leaderboard data36%
84Qwen2 VL 7b Instruct· Hugging Face Open LLM Leaderboard data35.9%
85DeepSeek R1 Distill Llama 70B· Hugging Face Open LLM Leaderboard data35.8%
86Qwen2.5 7B· Hugging Face Open LLM Leaderboard data35.8%
87GLM 4 9B 0414· Hugging Face Open LLM Leaderboard data35.8%
88gemma-2b· Epoch AI Benchmarking Hub data
Values from 2 sources
35.2%
89Qwen2.5 7B Instruct· Hugging Face Open LLM Leaderboard data34.9%
90Qwen 2 (7B)· Hugging Face Open LLM Leaderboard data34.7%
91Granite 3.2 8b Instruct· Hugging Face Open LLM Leaderboard data34.7%
92gemma-2-9b· Hugging Face Open LLM Leaderboard data34.1%
93Granite 3.1 8B Instruct· Hugging Face Open LLM Leaderboard data34.1%
94ChatGLM2 6B· Epoch AI Benchmarking Hub data33.7%
95DeepSeek LLM 67B Chat· Hugging Face Open LLM Leaderboard data33.2%
96Qwen1.5-14B-Chat· Hugging Face Open LLM Leaderboard data32.8%
97MN 12b Mag Mell R1· Hugging Face Open LLM Leaderboard data32.5%
98L3 8B Lunaris V1v1· Hugging Face Open LLM Leaderboard data32.1%
99L3 8B Stheno V3.2· Hugging Face Open LLM Leaderboard data32%
100SOLAR 10.7B Instruct v1.0· Hugging Face Open LLM Leaderboard data31.9%

Showing 51–100 of 179 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
DeepSeek V4.1 Flash BaseEM · 3-shot· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.86.1%
MiMo V2 Flash Baseofficial Base table · 3-shot· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.88.5%
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.91%
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.89.4%
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.89.6%
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.90.9%

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.