Skip to main content
Evaluation sources/IFBench（Artificial Analysis）
ObservingKnowledge & language

IFBench（Artificial Analysis）

Artificial Analysis · Public model evaluation results from IFBench（Artificial Analysis）.

Official evaluation
Source description

This source measures concrete delivery performance in Knowledge & language; raw scores are shown separately from the normalized capability score.

Limitation: Different versions, reasoning settings, and test sets may change scores; read them with the data date.

How it is used

Participating sources affect capability scores; reference, cross-reference, and observing sources are for comparison and verification only.

Model results from this source

Grok 4.30.8333333383.32026-11-05
Grok 4.20 (Reasoning)0.829251782.92026-11-05
MiniMax-M30.8285714382.92026-11-05
Nemotron 3 Ultra 550B A55B0.8136054481.42026-11-05
Grok 4.200.812244981.22026-10-11
Qwen3.7 Max0.8054421880.52026-11-05
Nemotron Cascade 2 30B A3B0.8040816380.42026-11-05
MiMo-V2.5-Pro0.7986394679.92026-11-05
Qwen3.5 397B-A17B0.787755178.82026-11-05
Gemini 3 Flash Preview0.7795918478.02026-11-05
Qwen3.7 Plus0.7795918478.02026-11-05
Gemini 3.1 Flash Lite0.7721088477.22026-11-05
Gemini 3.1 Pro Preview0.7714285777.12026-11-05
Qwen3.6 Max Preview0.7659863976.62026-11-05
DeepSeek V4 Pro0.7646258576.52026-11-05
GLM-5.10.7625850376.32026-11-05
Kimi K2.60.7598639576.02026-11-05
GPT-5.50.758503475.92026-11-05
Qwen3.5 122B-A10B0.7571428675.72026-11-05
MiniMax-M2.70.7571428675.72026-11-05
Qwen3.5 27B0.7557823175.62026-11-05
GPT-5 mini0.7544217775.42026-11-05
GPT-5.20.7544217775.42026-11-05
Qwen3.6 Plus0.7517006875.22026-11-05
GPT-5.40.7394557873.92026-11-05
Command A Plus0.7394557873.92026-11-05
Gemma 4 12B Base0.7353741573.52026-11-05
GLM-5.20.7333333373.32026-11-05
GPT-5.4 mini0.7326530673.32026-11-05
GLM-5-Turbo0.7319727973.22026-11-05
GPT-50.7306122473.12026-11-05
GPT-5.6 Sol0.7265306172.72026-11-05
Qwen3.5 35B-A3B0.7251700772.52026-11-05
MiniMax-M20.7231292572.32026-11-05
GLM-50.7231292572.32026-11-05
MiniMax-M2.50.7163265371.62026-11-05
Nemotron 3 Super 120B A12B0.7149659971.52026-11-05
o30.7142857171.42026-11-05
GPT-5.6 Terra0.712244971.22026-11-05
Solar Pro 30.7120181471.22026-11-05
Nemotron 3 Nano 30B A3B0.7108843571.12026-11-05
Qwen3 Max Thinking0.7074829970.72026-11-05
Gemini 3 Pro Preview0.7040816370.42026-11-05
o10.7034013670.32026-11-03
Kimi K2.50.7020408270.22026-11-05
MiniMax-M2.10.6986394669.92026-11-05
Mercury 20.6979591869.82026-11-05
gpt-oss-120b0.6897959269.02026-11-05
MiMo-V2-Pro0.6884353768.82026-11-05
Mistral Medium 3.50.687755168.82026-11-05
o4-mini0.6870748368.72026-10-11
o4 Mini High0.6870748368.72026-11-05
GLM-4.70.6789115667.92026-11-05
GPT-5 nano0.675510267.62026-11-05
Qwen3.6 27B0.675510267.62026-11-05
Step 3.7 Flash0.6727891267.32026-11-05
o3-mini0.6714285767.12026-10-11
o3 Mini High0.6714285767.12026-11-05
MiMo-V2.50.6714285767.12026-11-05
Qwen3.5 9B0.6673469466.72026-11-05
KAT-Coder-Pro V20.6666666766.72026-11-05
Step 3.5 Flash 26030.6653061266.52026-11-05
Nex-N2-Pro0.6619047666.22026-11-05
gpt-oss-20b0.6510204165.12026-11-05
Step 3.5 Flash0.6455782364.62026-11-05
Qwen3.6 35B-A3B0.6435374164.42026-11-05
MiMo-V2-Flash0.6421768764.22026-11-05
Claude Fable 50.6346938863.52026-11-05
Nemotron 3 Nano Omni 30B A3B Reasoning0.6319727963.22026-11-05
Hy3 preview0.6312925263.12026-11-05
Kimi K2.7 Code0.6312925263.12026-11-05
Claude Opus 4.80.6224489862.22026-11-05
GLM-5V-Turbo0.6108843561.12026-11-05
GLM-4.7-Flash0.6081632760.82026-11-05
DeepSeek V3.20.6068027260.72026-11-05
Claude Opus 4.70.5863945658.62026-11-05
Claude Opus 4.50.5795918458.02026-11-05
North Mini Code0.575510257.62026-11-05
Ling-2.6-flash0.5741496657.42026-11-05
Claude Sonnet 4.50.5727891257.32026-11-05
DeepSeek V3.1 Terminus0.5700680357.02026-11-05
Ling-2.6-1T0.5687074856.92026-11-05
Claude Sonnet 4.60.5659863956.62026-11-05
Trinity Large Thinking0.5625850356.32026-11-05
Claude Haiku 4.50.5428571454.32026-11-05
DeepSeek V3.2 Exp0.541496654.12026-11-05
MiMo-V2-Omni0.5353741553.52026-11-05
Claude Opus 4.60.5312925253.12026-11-05
Gemini 2.5 Flash0.5027210950.32026-11-05
Gemini 2.5 Flash-Lite0.4986394649.92026-11-05
Olmo 3 32B Think0.4911564649.12026-11-05
Gemini 2.5 Pro0.4870748348.72026-11-05
Grok 4.20 (Non-Reasoning)0.4782312947.82026-11-05
Qwen3 235B A22B Instruct 25070.4605442246.12026-11-05
Ring-2.6-1T0.4455782344.62026-11-05
Qwen3 Max0.441496644.12026-11-05
GLM-4.50.4408163344.12026-11-05
GLM-4.60.4340136143.42026-11-05
Llama 4 Maverick0.4299319743.02026-11-05
Qwen3 VL 235B A22B Instruct0.4265306142.72026-11-05
Kimi K2 09050.417006841.72026-11-05
Qwen3 30B A3B0.4149659941.52026-11-05
DeepSeek V3.10.4149659941.52026-11-05
DeepSeek V3 03240.4102040841.02026-11-05
Qwen3 14B0.4054421840.52026-11-05
Qwen3-Coder 480B-A35B Instruct0.404761940.52026-11-05
Gemini 2.0 Flash0.4020408240.22026-11-05
Qwen3-Next 80B-A3B Instruct0.3965986439.72026-11-05
Llama 4 Scout0.395238139.52026-11-05
Llama 3.3 Nemotron Super 49B v10.3945578239.52026-11-05
Mistral Medium 3.50.3925170139.32026-11-05
Qwen3 VL 32B Instruct0.3918367339.22026-11-05
DeepSeek-R10.3897959239.02026-11-05
Qwen3 235B-A22B0.3870748338.72026-11-05
Granite 4.1 8B0.3863945638.62026-11-05
GLM-4.5-Air0.375510237.62026-11-05
Qwen2.5 72B Instruct0.3687074836.92026-11-05
Command A0.3646258536.52026-11-05
Qwen3 32B0.3632653136.32026-11-05
Mistral Large 30.3619047636.22026-11-05
Qwen3 Coder Next0.3523809535.22026-11-05
Sarvam 105B0.3435374134.42026-11-05
GLM-4.5V0.3421768734.22026-11-05
Qwen3 8B0.3346938833.52026-11-05
GPT-40.3319727933.22026-11-05
Qwen3 VL 30B A3B Instruct0.3312925233.12026-11-05
Qwen3 30B A3B Instruct 25070.3306122433.12026-11-05
Qwen3-Coder 30B-A3B Instruct0.3265306132.72026-11-05
Qwen3 VL 8B Instruct0.3231292532.32026-11-05
Ministral 3 14B0.3204081632.02026-11-05
Nemotron Nano 12B v2 VL0.3190476231.92026-11-05
Reka Flash 30.3040816330.42026-11-05
GLM-4.6V0.3006802730.12026-11-05
Ministral 3 8B0.2911564629.12026-11-05
Nemotron Nano 9B v20.2761904827.62026-11-05
R1 Distill Llama 70B0.275510227.62026-11-05
Ministral 3 3B0.2680272126.82026-11-05
Sarvam 30B0.2646258526.52026-11-05
Mistral Small 30.2639455826.42026-11-05
Granite 4.0 Micro0.2476190524.82026-11-05
Phi 40.2353741523.52026-11-05

Frequently asked questions