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
1gemini-1.5-pro-001· Epoch AI Benchmarking Hub data89.2%
2Qwen 3 235B A22B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88.9%
3MiMo V2.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88.4%
4DeepSeek V3· Epoch AI Benchmarking Hub data87.5%
5Nova Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.9%
6Qwen2.5 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
84.5%
7DeepSeek V2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim84.3%
8Llama 3.1 405B· Epoch AI Benchmarking Hub data82.9%
9Nova Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim82.4%
10Qwen2 72B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
82.4%
11Phi-3 Medium 128K Instruct· Epoch AI Benchmarking Hub data
Values from 2 sources
81.4%
12Qwen2.5 72B· Epoch AI Benchmarking Hub data
Values from 2 sources
79.8%
13Nova Micro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim79.5%
14Phi-3 Small 8K Instruct· Epoch AI Benchmarking Hub data
Values from 2 sources
79.1%
15Qwen 2.5 14B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
78.2%
16GPT 4· Epoch AI Benchmarking Hub data75.1%
17Phi-3 Mini 4K Instruct· Epoch AI Benchmarking Hub data
Values from 2 sources
71.7%
18Yi 34B Chat· Epoch AI Benchmarking Hub data
Values from 2 sources
71.7%
19Qwen2.5 72B Instruct· Hugging Face Open LLM Leaderboard data61.9%
20GPT-3.5 Turbo· Epoch AI Benchmarking Hub data61.6%
21phi-2· Epoch AI Benchmarking Hub data
Values from 2 sources
59.4%
22EVA-Qwen2.5-72B-v0.2· Hugging Face Open LLM Leaderboard data59.1%
23Llama 2 70B Chat· Epoch AI Benchmarking Hub data58.5%
24Llama 2 13B Chat· Epoch AI Benchmarking Hub data58.2%
25Magnum V2 72B· Hugging Face Open LLM Leaderboard data57.9%
26internlm2-5-7b-chat· Hugging Face Open LLM Leaderboard data57%
27Qwen2 72B Dracarys· Hugging Face Open LLM Leaderboard data56.9%
28L3.3 Ms Nevoria 70b· Hugging Face Open LLM Leaderboard data56.6%
29Llama 3.3 70B Instruct· Hugging Face Open LLM Leaderboard data56.6%
30Qwen2-VL (72B) Instruct· Hugging Face Open LLM Leaderboard data56.3%
31L3.3 Nevoria R1 70b· Hugging Face Open LLM Leaderboard data56.2%
32Mistral 7B v0.1· Epoch AI Benchmarking Hub data
Values from 2 sources
56.1%
33Llama 3.1 70B Instruct· Hugging Face Open LLM Leaderboard data55.9%
34gemma-7b· Epoch AI Benchmarking Hub data
Values from 2 sources
55.1%
35Qwen-14B-Chat· Epoch AI Benchmarking Hub data55%
36Yi-34B· Epoch AI Benchmarking Hub data
Values from 2 sources
54.3%
37Qwen2.5 32B· Hugging Face Open LLM Leaderboard data54%
38Hermes 3 Llama 3.1 70B· Hugging Face Open LLM Leaderboard data53.8%
39QwQ 32B Preview· Hugging Face Open LLM Leaderboard data53.4%
40Mistral Large Instruct 2411· Hugging Face Open LLM Leaderboard data52.7%
41Phi 4· Hugging Face Open LLM Leaderboard data52.6%
42Qwen 2.5 Coder 32B Instruct· Hugging Face Open LLM Leaderboard data52.3%
43Qwen 2 (72B)· Hugging Face Open LLM Leaderboard data51.9%
44arcee-blitz· Hugging Face Open LLM Leaderboard data50.7%
45Llama 3 70B Instruct· Hugging Face Open LLM Leaderboard data50.2%
46Phi-3 Medium 4K Instruct· Hugging Face Open LLM Leaderboard data49.4%
47Gemma 2 27B IT· Hugging Face Open LLM Leaderboard data49.3%
48Qwen2.5 Math 72B Instruct· Hugging Face Open LLM Leaderboard data49%
49DeepHermes 3 Mistral 24B Preview· Hugging Face Open LLM Leaderboard data49%
50phi-3.5-moe-instruct· Hugging Face Open LLM Leaderboard data48.8%

Showing 1–50 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.