Skip to content

Benchmark

Arena ELO - Instruction Following

Instruction following benchmarks measure how closely models follow instructions. Higher scores are better.

Models measured
366
Scores recorded
423
Sources
1
IQ weight
1.18

Score distribution

1,294.5
Mean
1,332.7
Median
155.5
Std dev
1,056.7
10th percentile
1,465
90th percentile
780.7
Min
780.71,539.1
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.18 for chat models, measured over 366 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
101Mistral Medium 3.5· LMArena data1,415.3
102Grok 4.20 Beta 1· LMArena data1,415
103Gemini 3 FlashMinimal· LMArena data1,414.8
104Doubao Seed 2.0 Pro· LMArena data1,414.1
105Claude Haiku 4.520251001· LMArena data1,413.9
106Mistral Large 4· LMArena data1,413.7
107DeepSeek V3.2· LMArena data1,413.4
108ERNIE 5.00110· LMArena data1,412.9
109GLM 4.7· LMArena data1,411.7
110LongCat-Flash-Chat Exp2602· LMArena data1,411.1
111GPT-6 SolMax· LMArena data1,410.9
112GLM 4.6· LMArena data1,410.5
113GPT 5.2High· LMArena data1,409.1
114DeepSeek V3.2Thinking· LMArena data1,408.7
115Grok 3 Preview02-24· LMArena data1,408.4
116Qwen3 235B A22B Instruct 25072507· LMArena data1,407.8
117Claude Haiku 5.5High· LMArena data1,407.2
118Inkling 2 Small· LMArena data1,406.9
119GPT-5.5 Instant· LMArena data1,406.9
120Claude Opus 4Thinking 16K, 20250514· LMArena data1,406.2
121Qwen3 VL 235B· LMArena data1,406
122GPT-5.4 miniHigh· LMArena data1,405.1
123Gemini 2.5 Flash· LMArena data1,404.8
124MiniMax M2.7· LMArena data1,404.7
125Mistral Large 3· LMArena data1,404.6
126GPT-6 LunaMax· LMArena data1,404.5
127GLM 4.5· LMArena data1,404
128DeepSeek V3.1 TerminusThinking· LMArena data1,403.8
129GPT-4.5 Preview2025-02-27· LMArena data1,403.7
130ChatGPT-4o Latest20250326· LMArena data1,403.3
131Kimi K2 Thinking· LMArena data1,403.1
132GPT 5.2· LMArena data1,402.9
133Grok 4.7xHigh· LMArena data1,402.7
134Inkling Small· LMArena data1,402.1
135NVIDIA Nemotron 3.5 Super VL 120BNVFP4· LMArena data1,401.8
136DeepSeek V3.2 Exp· LMArena data1,401.3
137DeepSeek V3.2 ExpThinking· LMArena data1,401
138ERNIE-5.0-Preview1203· LMArena data1,400.9
139MiniMax-M2.1 Preview· LMArena data1,400.3
140DeepSeek V3.1Thinking· LMArena data1,400.2
141Grok 4.1· LMArena data1,399.9
142Qwen3.5 122B-A10B· LMArena data1,399.3
143Mistral Medium 3.12508· LMArena data1,397.9
144Qwen3 Max2025-09-23· LMArena data1,397.5
145Hunyuan Vision 1.5 Thinking· LMArena data1,397
146LongCat Flash Chat· LMArena data1,397
147Grok 4.1Thinking· LMArena data1,395.3
148Gemini 2.5 Flash Preview09-2025· LMArena data1,393.9
149ERNIE-5.0-Preview1022· LMArena data1,392.8
150MiMo V2 FlashNon-Thinking· LMArena data1,392.8

Showing 101–150 of 423 results.

Data credits: LMArena, CC BY 4.0 (licence)