Skip to content

Benchmark

Arena ELO Text Factuality - Coding

Coding benchmarks compare models on programming tasks. Higher scores are better.

Models measured
155
Scores recorded
174
Sources
1
IQ weight
1.95

Score distribution

1,491.4
Mean
1,494.7
Median
38
Std dev
1,437
10th percentile
1,534.3
90th percentile
1,344.9
Min
1,344.91,567
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.95 for chat models, measured over 155 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
101DeepSeek-V4-Pro PreviewHigh· LMArena data1,488.3
102Inkling 2 Small· LMArena data1,488.3
103GPT-5.4 miniHigh· LMArena data1,488.2
104Nemotron 3 UltraNVFP4· LMArena data1,488.1
105Qwen3 Max Preview· LMArena data1,487.4
106Gemma 4 26B A4B· LMArena data1,486.1
107Inkling Small· LMArena data1,486
108GPT 5.1· LMArena data1,485.9
109Claude Haiku 5.5High· LMArena data1,485.5
110Grok 4.20 Beta 1· LMArena data1,484.7
111GPT 5.2· LMArena data1,484.3
112ERNIE 5.00110· LMArena data1,483.5
113GPT-5.2 Chat20260210· LMArena data1,482.8
114Kimi K2 Thinking· LMArena data1,482
115GLM 4.6· LMArena data1,481.8
116GPT-5.5 Instant· LMArena data1,480.4
117GLM 4.7· LMArena data1,479.5
118DeepSeek-V4-Flash PreviewHigh· LMArena data1,479
119Gemini 3 FlashMinimal· LMArena data1,478.2
120Qwen3 235B A22B Instruct 25072507· LMArena data1,478.2
121MiMo V2 FlashNon-Thinking· LMArena data1,477.4
122Grok 4.7xHigh· LMArena data1,477.1
123DeepSeek V3.2 Exp· LMArena data1,476.9
124Grok 4.1Thinking· LMArena data1,475.4
125Doubao Seed 2.0 Pro· LMArena data1,475.2
126Solar Pro 4· LMArena data1,474
127Mistral Medium 3.12508· LMArena data1,473.4
128Step 3.5 Flash· LMArena data1,472.5
129NVIDIA Nemotron 3.5 Super VL 120BNVFP4· LMArena data1,472
130Gemini 2.5 Flash· LMArena data1,471
131Qwen3.5 122B-A10B· LMArena data1,470.9
132Grok 4.3· LMArena data1,469.1
133Grok 4.1· LMArena data1,468.4
134ChatGPT-4o Latest20250326· LMArena data1,466.7
135Qwen3.5 27B· LMArena data1,466.5
136GPT 5.4 NanoHigh· LMArena data1,464
137Muse Glimmer· LMArena data1,462.1
138MiniMax-M2.1 Preview· LMArena data1,461.6
139nova-experimental-chat11-10· LMArena data1,461.5
140Qwen3.5 Flash· LMArena data1,460.7
141ERNIE-5.0-Preview1203· LMArena data1,458.4
142GPT-5 miniHigh· LMArena data1,458.1
143Grok 4 FastReasoning· LMArena data1,457.3
144GPT-5.3 Chat· LMArena data1,457.1
145MiMo V2 FlashThinking· LMArena data1,456
146GPT-5 Chat· LMArena data1,455.7
147Qwen3 Next 80B A3B Instruct· LMArena data1,455.2
148Gemini 3.1 Flash Lite· LMArena data1,451
149GPT 5High· LMArena data1,451
150Qwen3.5 35B A3B· LMArena data1,450.6

Showing 101–150 of 174 results.

Data credits: LMArena, CC BY 4.0 (licence)