Skip to content
Models and systems measured
299
Scores recorded
328
Sources
5
IQ weight
1.01

Score distribution

54.6%
Mean
55.3%
Median
26.8%
Std dev
17.2%
10th percentile
85.2%
90th percentile
0.649%
Min
0.649%90.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.01 for chat models, measured over 292 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
51Nemotron 3 Super 120B A12BNeMo Evaluator / mostly NeMo Skills · published setting· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.83.7%
52DeepSeek V3.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim83.7%
53Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim83.6%
54MiniCPM-V 4.7 35B-A3B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim83.5%
55Trinity Large ThinkingTrinity-Large-Thinking Model Card· Reported by Arcee AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.83.4%
56DeepSeek V4 FlashDeepSeek V4 official model card · Non-Think· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.83%
57Qwen3 235B A22B Instruct 2507· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
83%
58LongCat Flash Chat· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
82.7%
59Qwen3 Next 80B A3Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim82.7%
60Seed OSS 36B Instruct· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim82.7%
61Gemma 4 26B A4B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim82.6%
62Gemma 4 26B A4BGemma 4 Technical Report · Table 5 · thinking mode unless noted· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.82.6%
63LongCat-Flash-Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim82.6%
64Kimi K2 0905· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim82.5%
65Qwen3.5 9B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
82.5%
66Qwen3 VL 32B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.82.1%
67MiniMax M2· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 3 sources
82%
68Nemotron 3.5 Lightning 30B A3B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
81.9%
69Nemotron 3.5 Lightning 30B A3Bofficial release table· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.81.9%
70MiniMax M2.7· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim81.8%
71Qwen3 VL 235B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.81.8%
72Sarvam 105B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81.7%
73GLM 4.5 Air· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
81.4%
74DeepSeek V3· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 3 sources
81.2%
75Kimi K2 Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
81.1%
76MiniMax M1 40K· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
81.1%
77MiniMax M1 80K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.81.1%
78Nova 2 Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim80.9%
79Nova 2 LiteAmazon Nova 2 Lite official launch chart / technical report · accuracy, v1· Reported by Amazon Web Services, Amazon AGI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.80.9%
80Qwen3 30B A3B2507, thinking· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim80.9%
81GPT OSS 120B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim80.8%
82GPT OSS 120Bhigh· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim80.7%
83Qwen3 Next 80B A3B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
80.6%
84Qwen3 Coder Next· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim80.5%
85Llama 4 Maverick· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim80.5%
86qwen3-vl-30bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.80.5%
87MiniMax M2.5· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim80.1%
88Sarvam-30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim80%
89Qwen3.5 Omni FlashQwen3.5-Omni release · no-thinking setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.79.9%
90Qwen3.5 4B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
79.1%
91Qwen3 VL 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.78.6%
92ERNIE-4.5-300B-A47B-PT· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim78.4%
93Nemotron 3 Nano 30B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
78.3%
94longcat-flash-lite· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 3 sources
78.3%
95Mistral Smalllatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78%
96qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.77.8%
97Granite 4.2 30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.6%
98Qwen: Qwen3 VL 8B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.77.3%
99Gemma 4 12B It· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.2%
100Gemini 2.0 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim76.4%

Showing 51–100 of 322 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 · 5-shot· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.74.1%
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.73.2%
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.76%
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.70.9%
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.68.6%
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.73.2%

Data credits: Hugging Face official benchmark leaderboards; licence varies by benchmark · Data by LLM Stats · OpenEvals/leaderboard-data, MIT (licence) · 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.