- input
- $0.065
- output
- $0.26
- Context
- 1Mtokens
- Listed
- 8mo 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 #171
- 1436
DeepSeek V4 Flash 0423Similar price - 1402
Qwen3 235B-A22BEarlier version - 1400
Qwen3 235B A22B Thinking 2507Nearby rank - 1399Qwen3 Next 80B A3B InstructNearby rank
- 1396Qwen3.5-Flash
- 1395DeepSeek V3 0324Nearby rank
- 1395Qwen3 VL 235B A22B ThinkingNearby rank
- 1314
Nemotron 3 Nano 30B A3BSimilar price - 1260
Nova Lite 1.0Similar price - 1167
Llama 3.2 3B InstructSimilar price
Level with Qwen3 235B-A22B (earlier version, overlapping 95% CIs) · Ahead of 3 of 4 similarly priced models
Arena WebDev
Best Arena rating per model · Higher is better
Arena #145
- 1585
MiniMax M3.1 FlashSimilar price - 1582DeepSeek V4 Flash 0423Similar price
- 1506
Hy3Similar price - 1358
Gemma 4 26B A4BSimilar price - 1253Qwen3.5-35B-A3BNearby rank
- 1245
GPT-5.1-Codex-MiniNearby rank - 1244Qwen3.5-Flash
- 1242
Grok 4.1 Fast (Reasoning)Nearby rank - 1233
Mistral Large 3 2512Nearby rank
Ahead of 0 of 4 similarly priced models
Arena Vision
Best Arena rating per model · Higher is better
Not ranked on Arena Vision yet
Arena Search
Best Arena rating per model · Higher is better
Not ranked on Arena Search yet
Agent Arena
Best IPS score per model · Higher is better
Not ranked on Agent Arena yet
FrontierMath-2025-02-28-Private
Best score per model · Higher is better
#37 of 58
- 8.3%GPT-5 NanoSimilar price
- 7.2%
Claude Opus 4.1Nearby rank - 6.2%Qwen3.5-Flash
- 5.9%Claude Haiku 4.5Nearby rank
- 5.5%GPT-4.1Nearby rank
- 1.0%GPT-4.1 NanoSimilar price
- 0.0%Llama 4 ScoutSimilar price
Ahead of 2 of 3 similarly priced models
FrontierMath-Tier-4-2025-07-01-Private
Best score per model · Higher is better
#39 of 46
- 2.1%GPT-5 NanoSimilar price
- 0.0%GPT-4.1Nearby rank
- 0.0%Qwen3 235B A22B Thinking 2507Nearby rank
- 0.0%Qwen3.5-Flash
- 0.0%Qwen3.6 FlashNearby rank
- 0.0%
GLM 4.7Nearby rank
Ahead of 0 of 1 similarly priced model
FrontierMath-Tiers-1-3-v2-Private
Best score per model · Higher is better
#81 of 87
- 78.9%GPT-6 LunaSimilar price
- 75.1%Claude Haiku 5.5Similar price
- 57.5%DeepSeek V4 Flash 0731Similar price
- 20.0%GPT-5 NanoSimilar price
- 19.3%Qwen3.7 FlashNearby rank
- 18.9%Qwen3 MaxNearby rank
- 18.2%Qwen3.5-Flash
- 12.6%Claude Opus 4.1Nearby rank
- 6.7%GPT-4.1 MiniNearby rank
Ahead of 0 of 4 similarly priced models
GPQA diamond
Best score per model · Higher is better
#81 of 161
- 91.0%DeepSeek V4 Flash 0731Similar price
- 82.5%GPT-5.5 InstantNearby rank
- 82.3%Claude Sonnet 4.5Nearby rank
- 82.3%Qwen3.5-Flash
- 82.3%Qwen3.7 FlashNearby rank
- 81.8%Gemini 3.1 Flash LiteNearby rank
- 73.2%Gemma 4 26B A4BSimilar price
- 69.4%GPT-5 NanoSimilar price
- 60.5%GLM 4.7 FlashSimilar price
- 56.8%Qwen3 8BPredecessor
+25.6 pts vs Qwen3 8B (predecessor) · Ahead of 3 of 4 similarly priced models
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#77 of 158
- 94.4%DeepSeek V4 Flash 0731Similar price
- 84.4%GPT-5.5Nearby rank
- 84.4%o3Nearby rank
- 84.4%Qwen3.5-Flash
- 84.4%Qwen3.6 FlashNearby rank
- 83.3%GLM 4.7Nearby rank
- 82.2%Gemma 4 26B A4BSimilar price
- 81.1%GPT-5 NanoSimilar price
- 58.3%GLM 4.7 FlashSimilar price
- 56.1%Qwen3 8BPredecessor
+28.3 pts vs Qwen3 8B (predecessor) · Ahead of 3 of 4 similarly priced models
SimpleQA Verified
Best score per model · Higher is better
#74 of 87
- 33.6%DeepSeek V4 Flash 0731Similar price
- 23.8%Claude Haiku 5.5Similar price
- 21.6%GPT-5 MiniNearby rank
- 20.3%Qwen3.5-Flash
- 20.0%Mistral Large 4Nearby rank
- 19.1%
Inkling SmallNearby rank - 11.7%GPT-5 NanoSimilar price
- 6.0%GPT-4.1 NanoSimilar price
Ahead of 2 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 #1711396
Level with Qwen3 235B-A22B (earlier version, overlapping 95% CIs)
- default139695% CI 1392 to 1400 · 61,168 votes
- Arena WebDevArena #1451244
- default124495% CI 1224 to 1263 · 1,322 votes
- FrontierMath-2025-02-28-Private#37 of 586.2%
- default6.2%
Source:Epoch AI evaluation - FrontierMath-Tier-4-2025-07-01-Private#39 of 460.0%
- default0.0%
Source:Epoch AI evaluation - FrontierMath-Tiers-1-3-v2-Private#81 of 8718.2%
- none18.2%
- default9.5%
Source:Epoch AI evaluation - GPQA diamond#81 of 16182.3%
+25.6 pts vs Qwen3 8B (predecessor)
- default82.3%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#77 of 15884.4%
+28.3 pts vs Qwen3 8B (predecessor)
- default84.4%
Source:Epoch AI evaluation - SimpleQA Verified#74 of 8720.3%
- default20.3%
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.