- input
- $0.71
- cached
- $0.71
- output
- $0.71
- Context
- 131Ktokens
- Released
- 1y ago
- Size
- 70Bparameters
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 #269
- 1416
Qwen3.5-122B-A10BSimilar price - 1415
Mistral Large 3 2512Similar price - 1383
GPT-4.1 MiniSimilar price - 1322
Llama 4 ScoutNearby rank - 1321
Molmo 2 8BNearby rank - 1318Llama 3.3 70B Instruct
- 1318GPT-4o-mini (2024-07-18)Nearby rank
- 1318gpt-oss-20bNearby rank
- 1293Llama 3.1 70B InstructPredecessor
- 1290
Gemma 2 27BSimilar price
+25 vs Llama 3.1 70B Instruct (predecessor) · Ahead of 1 of 4 similarly priced models
Arena WebDev
Best Arena rating per model · Higher is better
Not ranked on Arena WebDev 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
GPQA diamond
Best score per model · Higher is better
#143 of 161
- 88.5%
Inkling SmallSimilar price - 88.4%Qwen3.6 PlusSimilar price
- 65.8%GPT-4.1 MiniSimilar price
- 47.7%Gemma 3 27BNearby rank
- 47.6%Magistral Small 1.2Nearby rank
- 47.4%Llama 3.3 70B Instruct
- 44.2%Llama 3.1 70B InstructPredecessor
- 41.8%
Qwen TurboNearby rank - 36.5%Gemma 2 27BSimilar price
+3.3 pts vs Llama 3.1 70B Instruct (predecessor) · Ahead of 1 of 4 similarly priced models
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#147 of 158
- 93.3%Qwen3.6 PlusSimilar price
- 90.0%Inkling SmallSimilar price
- 44.7%GPT-4.1 MiniSimilar price
- 6.3%GPT-4o (2024-11-20)Nearby rank
- 6.1%Qwen TurboNearby rank
- 5.1%Llama 3.3 70B Instruct
- 4.3%
Claude Haiku 3.5Nearby rank - 3.6%Llama 3.1 70B InstructPredecessor
- 1.4%Gemma 2 27BSimilar price
+1.5 pts vs Llama 3.1 70B Instruct (predecessor) · 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 #2691318
+25 vs Llama 3.1 70B Instruct (predecessor)
- default131895% CI 1315 to 1322 · 54,482 votes
- GPQA diamond#143 of 16147.4%
+3.3 pts vs Llama 3.1 70B Instruct (predecessor)
- default47.4%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#147 of 1585.1%
+1.5 pts vs Llama 3.1 70B Instruct (predecessor)
- default5.1%
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.