GPT-5.1-Codex-Max: benchmark scores, price and ranking
GPT-5.1-Codex-Max from OpenAI ranks #204 of 743 LLMs on the LLMs Tiger aggregate benchmark score (50.2), based on 4 benchmark results captured up to 2026-10-13.
- Organisation
- OpenAI
- Type
- Frontier model
- Open weights
- No
- Released
- 2025-11-19 (source: epoch)
- Context window
- 400,000 tokens
- Cheapest API price
- $1.25 in / $10.00 out per million tokens (via azure, observed 2026-10-13T20:47Z)
- Aggregate rank
- #204 of 743 (score 50.2)
Relative to other models, GPT-5.1-Codex-Max is strongest on METR time horizon (#4 of 31) and weakest on ProofBench (#37 of 46).
Across the 4 benchmarks where at least ten models are scored, GPT-5.1-Codex-Max 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-Max benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| METR time horizon | 224 min | #4 of 31 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Terminal-Bench 2.0 | 60.4% | #4 of 28 | Epoch AI Benchmarking Hub | 2026-10-13 |
| ALE-Bench | 1,209 | #16 of 79 | Epoch AI Benchmarking Hub | 2026-10-13 |
| ProofBench | 9.0% | #37 of 46 | Epoch AI Benchmarking Hub | 2026-10-13 |
About GPT-5.1-Codex-Max
GPT-5.1-Codex-Max is a frontier model from OpenAI. It was released on 2025-11-19, 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 3 areas, and none is in the top tenth of its board.
Where GPT-5.1-Codex-Max stands
On our aggregate score, GPT-5.1-Codex-Max is #204 of 743 ranked models, around the middle of the table. Its score is 50.2; the scale is centred on 50, so it sits 0.2 points above the typical model. That beats 73% of the ranked field. Among the 88 ranked OpenAI models it is #28. The next one up is chatgpt-4o-latest (2025-03-29) at 50.2. The next one down is gpt-4.5-preview at 50.2.
GPT-5.1-Codex-Max, benchmark by benchmark
METR time horizon puts GPT-5.1-Codex-Max at 224 min, #4 of 31. That beats 87% of the models tested, but 821 minutes short of Claude Mythos Preview (Early) (1,045 min). The results either side are Gemini 3 Pro Preview (224 min) and GPT-5 (high) (203 min). It covers length of task (minutes) done at 50% success. The board median is 23 min, so GPT-5.1-Codex-Max is 201 minutes above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
On Terminal-Bench 2.0, GPT-5.1-Codex-Max reaches 60.4%. It ranks #4 of 28, ahead of 86% of the field, and 9.0 points behind Gemini 3 Pro Preview at 69.4%. The results either side are GPT-5.1 Codex Mini (61.6%) and Claude Opus 4.5 (128k thinking) (59.1%). It covers real terminal tasks (agent + model). The board median is 37.3%, so GPT-5.1-Codex-Max is 23.1 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
GPT-5.1-Codex-Max manages 1,209 on ALE-Bench, good for #16 of 79. GPT-6 Astra (max) leads at 2,951, 1,742 points further up, and 80% of models sit below. The results either side are GPT-5.1 Codex (1,245) and GPT-5.1 (high) (1,192). It covers AtCoder heuristic-optimisation contests (performance rating). The board median is 764, so GPT-5.1-Codex-Max is 445 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
ProofBench is a weak spot. GPT-5.1-Codex-Max scores 9.0%, #37 of 46, behind 78% of the models measured. The leader, Claude Fable 5.1 (max), reaches 100.0%. It covers writing mathematical proofs. The board median is 21.0%, so GPT-5.1-Codex-Max is 12.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Software engineering: strong, ahead of 83% of the field on average across 2 benchmarks. Its best board here is Terminal-Bench 2.0 (#4 of 28) and its weakest is ALE-Bench (#16 of 79).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so GPT-5.1-Codex-Max costs more than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), DeepSeek V4 Flash 0731 (max) ($0.016, 53.1). 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-5.1 (high) on 2025-11-12, which scores 52.7. The next one was gpt-5.2-2025-12-11-high on 2025-12-11, at 52.1.
Reading these numbers
The 4 scores on this page come from 1 source: Epoch AI Benchmarking Hub (4). 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
- #201 Codex + GPT-5.6 Sol (50.3)
- #202 DeepSeek V3.2 Reasoner (50.3)
- #203 chatgpt-4o-latest (2025-03-29) (50.2)
- #205 gpt-4.5-preview (50.2)
- #206 TTS(Bo16) (50.2)
- #207 gpt-4-1106-preview (50.2)
More from OpenAI
- GPT-6 Astra (max) (#2, 64.0)
- GPT-6.1 Sol (max) (#5, 60.6)
- GPT-5.6 Sol (max) (#6, 60.1)
- GPT-6 Sol (max) (#7, 60.0)
- GPT-5.5 (xhigh) (#11, 58.0)
- GPT-5.6 Terra (max) (#12, 57.8)
Compare it on the live leaderboard → · How the aggregate score works