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
251Granite 3.0 8B Instruct· Hugging Face Open LLM Leaderboard data27.3%
252MN 12b Mag Mell R1· Hugging Face Open LLM Leaderboard data27.1%
253Yi-6B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
26.5%
254fimbulvetr-11b-v2· Hugging Face Open LLM Leaderboard data25.6%
255OpenChat 3.5· Hugging Face Open LLM Leaderboard data25.5%
256Qwen2.5 3B Instruct· Hugging Face Open LLM Leaderboard data25.1%
257granite-3-1-8b-base· Hugging Face Open LLM Leaderboard data24.8%
258Llama 3.2 3B· Hugging Face Open LLM Leaderboard data
Values from 2 sources
24.4%
259GLM-4-9b-chat· Hugging Face Open LLM Leaderboard data24.1%
260SOLAR 10.7B Instruct v1.0· Hugging Face Open LLM Leaderboard data23.8%
261Llemma 7b· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim23.5%
262Mistral (7B) Instruct v0.3· Hugging Face Open LLM Leaderboard data23.1%
263Nous-Hermes-2-Mixtral-8x7B-SFT· Hugging Face Open LLM Leaderboard data23%
264OpenHermes 2.5 Mistral 7B· Hugging Face Open LLM Leaderboard data22.8%
265NousResearch: Hermes 2 Pro - Llama-3 8B· Hugging Face Open LLM Leaderboard data22.8%
266Qwen2 1.5b Instruct· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
22.6%
267Qwen 2 (1.5B)· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
22.6%
268Mistral 7B v0.1· Hugging Face Open LLM Leaderboard data22.4%
269mistral-7b-v0.3· Hugging Face Open LLM Leaderboard data21.7%
270gemma-7b· Hugging Face Open LLM Leaderboard data21.6%
271OpenHermes-2-Mistral-7B· Hugging Face Open LLM Leaderboard data21.5%
272Qwen1.5-7B· Hugging Face Open LLM Leaderboard data21.3%
273Yi-6B200k· Hugging Face Open LLM Leaderboard data20.5%
274Qwen2.5 Math 7B Instruct· Hugging Face Open LLM Leaderboard data20.2%
275Granite 3.1 2B Instruct· Hugging Face Open LLM Leaderboard data20.2%
276Granite 3.0 2B Instruct· Hugging Face Open LLM Leaderboard data20.2%
277Qwen2.5 1.5B Instruct· Hugging Face Open LLM Leaderboard data20%
278Zephyr 7B Beta· Hugging Face Open LLM Leaderboard data19.8%
279Mistral-7B-OpenOrca· Hugging Face Open LLM Leaderboard data18.4%
280phi-2· Hugging Face Open LLM Leaderboard data18.1%
281Gemma 1.1 7B IT· Hugging Face Open LLM Leaderboard data17.6%
282Gemma 2 2B IT· Hugging Face Open LLM Leaderboard data17.2%
283Qwen1.5-4B· Hugging Face Open LLM Leaderboard data16.2%
284ERNIE 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim16%
285Llama-2-70b-chat-hf· Hugging Face Open LLM Leaderboard data15.9%
286Mistral (7B) Instruct v0.1· Hugging Face Open LLM Leaderboard data15.7%
287Qwen1.5-4B-Chat· Hugging Face Open LLM Leaderboard data15.5%
288Starcoder2 15b· Hugging Face Open LLM Leaderboard data15%
289Gemma 3 1b it· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim14.7%
290DeepSeek R1 Distill Qwen 7B· Hugging Face Open LLM Leaderboard data14.7%
291gemma2-2b· Hugging Face Open LLM Leaderboard data13.1%
292granite-3.0-3b-a800m-instruct· Hugging Face Open LLM Leaderboard data12.8%
293vicuna-7b-v1.5· Hugging Face Open LLM Leaderboard data12.7%
294DeepSeek R1 Distill Llama 8B· Hugging Face Open LLM Leaderboard data12.1%
295Llama 3.2 1B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
12%
296Nous-Hermes-llama-2-7b· Hugging Face Open LLM Leaderboard data10.4%
297Llama-2-13b-chat-hf· Hugging Face Open LLM Leaderboard data10.3%
298Qwen1.5-1.8B· Hugging Face Open LLM Leaderboard data9.8%
299NexusRaven-V2-13B· Hugging Face Open LLM Leaderboard data9.7%
300Qwen1.5-1.8B-Chat· Hugging Face Open LLM Leaderboard data8.9%

Showing 251–300 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.