- input
- $1.25
- cached
- $0.20
- output
- $2.50
- Context
- 1Mtokens
- Released
- 6mo ago
Cost/1M tokens
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Arena leaderboards and other sourced evaluations appear below; missing scores are not zero.
How it ranks
Against its predecessor, similarly priced models and the models ranked around it.
DeepSWE 1.1
Best pass@1 per model · Higher is better
Not evaluated in DeepSWE 1.1
Arena Text
Best Arena rating per model · Higher is better
Arena #95
- 1489
Gemini 3.7 FlashSimilar price - 1457
GLM 5Similar price - 1448
Step 5 PreviewSimilar price - 1447
GPT-5.4 MiniSimilar price - 1443
Qwen3.6 PlusNearby rank - 1442
Grok 4.7Nearby rank - 1442Grok 4.3
- 1441Qwen3.5 397B A17BNearby rank
- 1441GLM 4.7Nearby rank
Ahead of 0 of 4 similarly priced models
Arena WebDev
Best Arena rating per model · Higher is better
Arena #123
- 1588Gemini 3.7 FlashSimilar price
- 1573Step 5 PreviewSimilar price
- 1435GLM 5Similar price
- 1398GPT-5.4 MiniSimilar price
- 1358Gemma 4 26B A4BNearby rank
- 1358
Hy3 previewNearby rank - 1357Grok 4.3
- 1357Qwen3.5-27BNearby rank
- 1350
Laguna M.1Nearby rank
Ahead of 0 of 4 similarly priced models
Arena Vision
Best Arena rating per model · Higher is better
Arena #64
- 1294Gemini 3.7 FlashSimilar price
- 1250GPT-5.4 MiniSimilar price
- 1245Step 5 PreviewSimilar price
- 1242GPT-5.2Nearby rank
- 1242Gemma 4 26B A4BNearby rank
- 1242Grok 4.3
- 1235GPT-6 LunaNearby rank
- 1235Gemini 3.1 Flash Lite PreviewNearby rank
- 1019
Nova Pro 1.0Similar price
Ahead of 1 of 4 similarly priced models
Arena Search
Best Arena rating per model · Higher is better
Arena #24
- 1205Grok 4.5Similar price
- 1201Gemini 3 Pro PreviewNearby rank
- 1194
Claude Opus 4.8Nearby rank - 1194Grok 4.3
- 1192
ERNIE 5.1Nearby rank - 1142
Sonar ProNearby rank
Ahead of 0 of 1 similarly priced model
Arena Document
Best Arena rating per model · Higher is better
Not ranked on Arena Document yet
Agent Arena
Best IPS score per model · Higher is better
Not ranked on Agent Arena yet
FrontierMath-Tier-4-v2-Private
Best score per model · Higher is better
#56 of 72
- 36.6%Gemini 3.7 FlashSimilar price
- 29.3%GLM 5.2Similar price
- 17.1%Grok 4.20 (Reasoning)Nearby rank
- 17.1%GLM 5.3 FlashNearby rank
- 14.6%Grok 4.3
- 12.2%
Kimi K2.7 CodeNearby rank - 12.2%GPT-5 MiniNearby rank
- 9.8%GPT-5.4 MiniSimilar price
- 4.9%
InklingSimilar price
Ahead of 2 of 4 similarly priced models
FrontierMath-Tiers-1-3-v2-Private
Best score per model · Higher is better
#60 of 87
- 71.6%Gemini 3.7 FlashSimilar price
- 59.2%GLM 5.2Similar price
- 51.2%GPT-5.4 MiniSimilar price
- 44.9%GPT-5.4 NanoNearby rank
- 44.9%Grok 4.20 (Reasoning)Nearby rank
- 42.8%Grok 4.3
- 38.2%Qwen3.6 PlusNearby rank
- 36.8%GLM 5.1Nearby rank
- 33.3%InklingSimilar price
Ahead of 1 of 4 similarly priced models
GPQA diamond
Best score per model · Higher is better
#50 of 161
- 94.8%Gemini 3.7 FlashSimilar price
- 89.4%Gemini 3 Flash PreviewNearby rank
- 89.3%Grok 4.20 (Reasoning)Nearby rank
- 88.8%Grok 4.3
- 88.5%Inkling SmallNearby rank
- 88.4%Qwen3.6 PlusNearby rank
- 88.3%InklingSimilar price
- 87.8%GLM 5Similar price
- 86.9%GPT-5.4 MiniSimilar price
Ahead of 3 of 4 similarly priced models
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#47 of 158
- 97.2%Gemini 3.7 FlashSimilar price
- 93.3%Qwen3.6 PlusNearby rank
- 93.3%Qwen3.7 PlusNearby rank
- 93.3%Grok 4.3
- 93.3%GLM 5.1Nearby rank
- 92.2%Grok 4.20 (Reasoning)Nearby rank
- 88.9%GPT-5.4 MiniSimilar price
- 88.9%InklingSimilar price
- 80.0%GLM 5Similar price
Ahead of 3 of 4 similarly priced models
SimpleQA Verified
Best score per model · Higher is better
#63 of 87
- 69.2%Gemini 3.7 FlashSimilar price
- 40.3%InklingSimilar price
- 34.2%GLM 5.2Similar price
- 33.7%Claude Sonnet 5Nearby rank
- 33.6%
DeepSeek V4 Flash 0731Nearby rank - 33.2%Grok 4.3
- 32.2%GLM 4.7Nearby rank
- 31.1%GPT-4.1Nearby rank
- 29.4%GPT-5.4 MiniSimilar price
Ahead of 1 of 4 similarly priced models
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
All published scores
- Arena TextArena #951442
- default144295% CI 1438 to 1445 · 70,242 votes
- Arena WebDevArena #1231357
- default135795% CI 1351 to 1364 · 14,690 votes
- Arena VisionArena #641242
- default124295% CI 1236 to 1247 · 29,224 votes
- Arena SearchArena #241194
- default119495% CI 1189 to 1199 · 122,703 votes
- FrontierMath-Tier-4-v2-Private#56 of 7214.6%
- high14.6%
Source:Epoch AI evaluation - FrontierMath-Tiers-1-3-v2-Private#60 of 8742.8%
- high42.8%
Source:Epoch AI evaluation - GPQA diamond#50 of 16188.8%
- high88.8%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#47 of 15893.3%
- high93.3%
Source:Epoch AI evaluation - SimpleQA Verified#63 of 8733.2%
- high33.2%
Source:Epoch AI evaluation
Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.
Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.