GPT-5.1 Codex: benchmark scores, price and ranking
GPT-5.1 Codex from OpenAI ranks #179 of 743 LLMs on the LLMs Tiger aggregate benchmark score (50.6), based on 4 benchmark results captured up to 2026-10-14.
- Organisation
- OpenAI
- Type
- Frontier model
- Open weights
- No
- Released
- 2025-11-12 (source: epoch)
- Context window
- 400,000 tokens
- Cheapest API price
- $1.25 in / $10.00 out per million tokens (via azure, observed 2026-10-14T22:47Z)
- Aggregate rank
- #179 of 743 (score 50.6)
Relative to other models, GPT-5.1 Codex is strongest on ALE-Bench (#16 of 81) and weakest on WebDev Arena (#50 of 67).
Across the 4 benchmarks where at least ten models are scored, GPT-5.1 Codex is in the top 10% on 0 and in the top half on 3.
Its cheapest listed input price, $1.25 per million tokens, is lower than that of 26% of the 427 models with a listed price.
GPT-5.1 Codex benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| ALE-Bench | 1,245 | #16 of 81 | Epoch AI Benchmarking Hub | 2026-10-14 |
| Terminal-Bench 2.0 | 57.8% | #6 of 28 | Epoch AI Benchmarking Hub | 2026-10-14 |
| SWE-bench Verified | 66.0% | #25 of 73 | SWE-bench Verified leaderboard | 2026-10-14 |
| WebDev Arena | 1,336 | #50 of 67 | Epoch AI Benchmarking Hub | 2026-10-14 |
About GPT-5.1 Codex
GPT-5.1 Codex is a frontier model from OpenAI. It was released on 2025-11-12, according to Epoch AI. It accepts up to 400,000 tokens of input at once. The cheapest API listing we track charges $1.25 per million input tokens and $10.00 per million output tokens, through azure. We hold 4 benchmark results for it across 1 area, and none is in the top tenth of its board.
Where GPT-5.1 Codex stands
On our aggregate score, GPT-5.1 Codex is #179 of 743 ranked models, in the top quarter. Its score is 50.6; the scale is centred on 50, so it sits 0.6 points above the typical model. That beats 76% of the ranked field. Among the 88 ranked OpenAI models it is #24. The next one up is o3-mini_1.0 at 50.7. The next one down is chatgpt-4o-01-29-2025 at 50.6.
GPT-5.1 Codex, benchmark by benchmark
ALE-Bench puts GPT-5.1 Codex at 1,245, #16 of 81. That beats 80% of the models tested, but 1,706 points short of GPT-6 Astra (max) (2,951). The results either side are Gemini 3.8 Flash (high) (1,270) and MiMo-V2.6 Flash (1,244). It covers AtCoder heuristic-optimisation contests (performance rating). The board median is 766, so GPT-5.1 Codex is 479 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-14.
On Terminal-Bench 2.0, GPT-5.1 Codex reaches 57.8%. It ranks #6 of 28, ahead of 79% of the field, and 11.6 points behind Gemini 3 Pro Preview at 69.4%. The results either side are Claude Opus 4.5 (128k thinking) (59.1%) and grok-4-20 (57.3%). It covers real terminal tasks (agent + model). The board median is 37.3%, so GPT-5.1 Codex is 20.5 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-14.
GPT-5.1 Codex manages 66.0% on SWE-bench Verified, good for #25 of 73. Claude Opus 4.7 (max) leads at 83.5%, 17.5 points further up, and 66% of models sit below. The results either side are Claude 4.5 Haiku (66.6%) and Kimi K2 (65.4%). It covers real GitHub issues resolved. The board median is 56.4%, so GPT-5.1 Codex is 9.6 points above it. Source: SWE-bench Verified leaderboard, captured 2026-10-14.
GPT-5.1 Codex lands below the middle on WebDev Arena: 1,336, #50 of 67, with 73% of the field scoring higher. Claude Opus 5.5 (max) leads at 1,820; the closest result above is Kimi K2 Thinking Turbo at 1,337. It covers building web apps, crowd-voted (Elo). The board median is 1,433, so GPT-5.1 Codex is 97 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-14.
Strengths and weaknesses
Software engineering: solid, ahead of 62% of the field on average across 4 benchmarks. Its best board here is ALE-Bench (#16 of 81) and its weakest is WebDev Arena (#50 of 67).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so GPT-5.1 Codex costs more than the typical listing. Models that score within 1.5 points or better and cost less: DeepSeek V4.1 Flash (high) ($0.010, 49.7), Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4 Flash 0731 (max) ($0.016, 53.0). Similar scores cost more on glm-5p1 ($1.40) and Qwen3.8 Max (0902) (xhigh) ($1.65).
Release history
The OpenAI model released before it was GPT-5-codex (high) on 2025-09-15, which scores 50.5. The next one was GPT-5.1 Codex Mini on 2025-11-12, at 48.7.
Reading these numbers
The 4 scores on this page come from 2 sources: Epoch AI Benchmarking Hub (3), SWE-bench Verified leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 4 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #176 gemini-exp-1206 (50.6)
- #177 MiniMax-Text-01 (50.6)
- #178 Kimi K2.5 (50.6)
- #180 chatgpt-4o-01-29-2025 (50.6)
- #181 Claude Sonnet 4.5 (59k thinking) (50.6)
- #182 Gemini 3 Pro (50.6)
More from OpenAI
- GPT-6 Astra (max) (#2, 63.9)
- GPT-6.1 Sol (max) (#3, 62.0)
- GPT-5.6 Sol (max) (#8, 59.9)
- GPT-6 Sol (max) (#9, 59.9)
- GPT-5.5 (xhigh) (#11, 57.8)
- GPT-5.6 Terra (max) (#12, 57.6)
Compare it on the live leaderboard → · How the aggregate score works