- input
- $2.00
- cached
- $0.50
- output
- $6.00
- Context
- 500Ktokens
- Released
- 1mo 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 #94
- 1483
Kimi K3.1 ProSimilar price - 1478
Gemini 3.5 FlashSimilar price - 1456
Grok 4.6Predecessor - 1455
GPT-5.1Similar price - 1443
InklingNearby rank - 1443
Qwen3.6 PlusNearby rank - 1442Grok 4.7
- 1442Grok 4.3Nearby rank
- 1441Qwen3.5 397B A17BNearby rank
- 1427
Mistral Medium 3.5Similar price
-15 vs Grok 4.6 (predecessor) · Ahead of 1 of 4 similarly priced models
Arena WebDev
Best Arena rating per model · Higher is better
Arena #23
- 1676Qwen3.8 Max (0902)Similar price
- 1649
Muse WonderNearby rank - 1646Inkling 2 SmallNearby rank
- 1641Grok 4.7
- 1638
MiMo-V2.6-FlashNearby rank - 1632
Hy4 previewNearby rank - 1618Grok 4.6Predecessor
- 1500Gemini 3.5 FlashSimilar price
- 1417GPT-5Similar price
- 1263Mistral Medium 3.5Similar price
+23 vs Grok 4.6 (predecessor) · Ahead of 3 of 4 similarly priced models
Arena Vision
Best Arena rating per model · Higher is better
Arena #55
- 1281Gemini 3.5 FlashSimilar price
- 1263Grok 4.6Predecessor
- 1263
Claude Sonnet 5.5Similar price - 1251GPT-5.1Similar price
- 1250GPT-5.4 MiniNearby rank
- 1249Grok 4.7
- 1248MiMo-V2.6-FlashNearby rank
- 1247Gemini 2.5 ProNearby rank
- 1199Mistral Medium 3.5Similar price
Level with Grok 4.6 (predecessor, overlapping 95% CIs) · Ahead of 1 of 4 similarly priced models
Arena Search
Best Arena rating per model · Higher is better
Not ranked on Arena Search yet
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
Arena #17
- +0.170Gemini 4 CarbonSimilar price
- +0.160Claude Sonnet 5.5Similar price
- +0.049Kimi K3.1 ProSimilar price
- +0.046GPT-5.6 SolNearby rank
- +0.026Grok 4.7
- +0.025Inkling 2 SmallNearby rank
- +0.024MiMo-V2.6-ProNearby rank
- -0.002Grok 4.6Predecessor
- -0.137Mistral Medium 3.5Similar price
+0.027 vs Grok 4.6 (predecessor) · Ahead of 1 of 4 similarly priced models
ARC-AGI-2
Best score per model · Higher is better
#31 of 85
- 83.9%Claude Sonnet 5.5Similar price
- 72.1%Gemini 3.5 FlashSimilar price
- 67.1%Grok 4.6Predecessor
- 64.6%Claude Opus 4.6Nearby rank
- 61.4%
DeepSeek V4 Flash 0731Nearby rank - 61.4%Grok 4.7
- 61.3%Claude Haiku 5.5Nearby rank
- 61.3%DeepSeek V4 Pro 0813Nearby rank
- 60.4%Kimi K3Similar price
- 17.6%GPT-5.1Similar price
-5.7 pts vs Grok 4.6 (predecessor) · Ahead of 2 of 4 similarly priced models
FrontierMath-Tier-4-v2-Private
Best score per model · Higher is better
#51 of 72
- 80.5%Claude Sonnet 5.5Similar price
- 34.1%Qwen3.8 Max (0902)Similar price
- 31.7%Grok 4.6Predecessor
- 26.8%Gemini 3.5 FlashSimilar price
- 22.0%GPT-5Similar price
- 17.1%Gemini 3 Flash PreviewNearby rank
- 17.1%Inkling SmallNearby rank
- 17.1%Grok 4.7
- 17.1%Grok 4.20 (Reasoning)Nearby rank
- 17.1%
GLM 5.3 FlashNearby rank
-14.6 pts vs Grok 4.6 (predecessor) · Ahead of 0 of 4 similarly priced models
FrontierMath-Tiers-1-3-v2-Private
Best score per model · Higher is better
#52 of 87
- 88.8%Claude Sonnet 5.5Similar price
- 66.0%Grok 4.6Predecessor
- 65.6%Qwen3.8 Max (0902)Similar price
- 62.8%Gemini 3.5 FlashSimilar price
- 55.4%GPT-5Similar price
- 54.0%Kimi K2.7 CodeNearby rank
- 53.0%Grok 4.7
- 51.2%Gemini 3 Flash PreviewNearby rank
- 51.2%GPT-5.4 MiniNearby rank
-13.0 pts vs Grok 4.6 (predecessor) · Ahead of 0 of 4 similarly priced models
GPQA diamond
Best score per model · Higher is better
#23 of 161
- 94.0%Grok 4.6Predecessor
- 93.1%Kimi K3Nearby rank
- 92.8%Gemini 3.5 FlashSimilar price
- 92.7%Grok 4.7
- 92.7%
Qwen3.8 MaxNearby rank - 92.6%Gemini 3 Pro PreviewNearby rank
- 92.3%Qwen3.8 Max (0902)Similar price
- 87.6%GPT-5.1Similar price
- 49.0%Mistral Large 2407Similar price
-1.3 pts vs Grok 4.6 (predecessor) · Ahead of 3 of 4 similarly priced models
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#28 of 158
- 100.0%Qwen3.8 Max (0902)Similar price
- 99.2%Grok 4.6Predecessor
- 98.3%Mistral Large 4Nearby rank
- 98.3%GPT-5.6 LunaNearby rank
- 98.1%Grok 4.7
- 97.8%Claude Opus 4.7Nearby rank
- 97.8%GPT-5.4Nearby rank
- 95.6%Gemini 3.5 FlashSimilar price
- 91.4%GPT-5Similar price
- 8.5%Mistral Large 2407Similar price
-1.1 pts vs Grok 4.6 (predecessor) · Ahead of 3 of 4 similarly priced models
SimpleQA Verified
Best score per model · Higher is better
#22 of 87
- 66.2%Gemini 3.5 FlashSimilar price
- 57.8%Muse Spark 1.1Nearby rank
- 57.3%GPT-6.1 TerraNearby rank
- 56.0%Grok 4.7
- 55.8%Qwen3.7 MaxNearby rank
- 53.0%Claude Opus 4.8Nearby rank
- 50.1%GPT-5Similar price
- 49.3%Grok 4.6Predecessor
- 47.3%Qwen3.8 Max (0902)Similar price
- 46.5%Claude Sonnet 5.5Similar price
+6.7 pts vs Grok 4.6 (predecessor) · Ahead of 3 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.
Reasoning effort
ARC-AGI-2
Score by reasoning effort · Higher is better
All published scores
- Arena TextArena #941442
-15 vs Grok 4.6 (predecessor)
- xhigh144295% CI 1437 to 1447 · 21,586 votes
- Arena WebDevArena #231641
+23 vs Grok 4.6 (predecessor)
- xhigh164195% CI 1633 to 1649 · 8,125 votes
- Arena VisionArena #551249
Level with Grok 4.6 (predecessor, overlapping 95% CIs)
- xhigh124995% CI 1240 to 1258 · 6,181 votes
- Agent ArenaArena #17+0.026
+0.027 vs Grok 4.6 (predecessor)
- xhigh+0.02695% CI +0.011 to +0.040 · 3,757,735 observations
- ARC-AGI-2#31 of 8561.4%
-5.7 pts vs Grok 4.6 (predecessor)
- low16.7%
- medium58.8%
- high58.3%
- xhigh61.4%
- FrontierMath-Tier-4-v2-Private#51 of 7217.1%
-14.6 pts vs Grok 4.6 (predecessor)
- xhigh17.1%
Source:Epoch AI evaluation - FrontierMath-Tiers-1-3-v2-Private#52 of 8753.0%
-13.0 pts vs Grok 4.6 (predecessor)
- xhigh53.0%
Source:Epoch AI evaluation - GPQA diamond#23 of 16192.7%
-1.3 pts vs Grok 4.6 (predecessor)
- xhigh92.7%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#28 of 15898.1%
-1.1 pts vs Grok 4.6 (predecessor)
- xhigh98.1%
Source:Epoch AI evaluation - SimpleQA Verified#22 of 8756.0%
+6.7 pts vs Grok 4.6 (predecessor)
- xhigh56.0%
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.