GPT-5.5
- Input price
- $5.00
- Per 1 million tokens (USD)
- Output price
- $30.00
- Per 1 million tokens (USD)
- Effort levels
- 5total
- Default: Med
- Benchmark results
- 14total
- Benchmark types: 9
Model information
- API model ID
- gpt-5.5
- release date
- 2026-04-24
- effort
- None / Low / Med (default) / High / Xhigh
- Effort source
- Based on reasoning effort on the OpenAI model page (developers.openai.com/api/docs/models/gpt-5.5, retrieved 2026-11-13). max is absent from the list.
- Claude Code
- unavailable
- Codex
- available
- Availability notes
- The Codex model page (learn.chatgpt.com/docs/models) under "Other models" states 'GPT-5.5 remains available through the OpenAI API and in Codex sessions authenticated with an API key.', so this is true because the official list says it can be selected in Codex sessions authenticated with an API key (the same page states 'GPT-5.5 retires from Codex with ChatGPT sign-in on October 14, 2026', so it cannot be selected in sessions with ChatGPT sign-in). Claude Code's official model list (code.claude.com/docs/en/model-config alias table) contains only Anthropic models, so claudeCode is false (connections via a gateway are not counted as official options).
- Availability source
- https://learn.chatgpt.com/docs/models
Price (USD per 1 million tokens)
Prices do not vary by effort; token consumption does.
| input | $5.00 |
|---|---|
| output | $30.00 |
| cache read | $0.50 |
| cache write | — |
For more than 272K input tokens, the entire request is charged at 2x input and 1.5x output. Regional processing (data residency) costs 10% more. Cache is limited to extended prompt caching (changelog). The cache write column in the pricing table is "-".
Text tokens Per 1M tokens | Input $5.00 | Cached input $0.50 | Output $30.00Source: https://developers.openai.com/api/docs/models/gpt-5.5
Benchmark results
| Benchmark | effort | Score | Source cost (metric) | measured/reported by | source | Conditions and extraction method |
|---|---|---|---|---|---|---|
| GPQA DiamondNone | None | 77.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0third-party · Retrieved 2026-11-12 | Run by Epoch AI (third-party measurement). Source label "GPT-5.5 (no thinking)". effort is indicated by the suffix _none in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptgpqa_diamond.csv: Model version=gpt-5.5_none, Best score (across scorers)=0.7727272727272727, stderr=0.029857515673386438, Started at=2026-08-07T00:57:11.000ZLocation gpqa_diamond.csv, data row 84 (file line 137), id=KesKa5EXtFG7H4UMBFzgCh, Model version=gpt-5.5_none |
| GPQA DiamondLow | Low | 90.7% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0third-party · Retrieved 2026-11-12 | Run by Epoch AI (third-party measurement). Source label "GPT-5.5 (low)". effort is indicated by the suffix _low in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptgpqa_diamond.csv: Model version=gpt-5.5_low, Best score (across scorers)=0.9065656565656566, stderr=0.017532658377721708, Started at=2026-05-05T18:00:18.624ZLocation gpqa_diamond.csv, data row 178 (file line 248), id=2CdomqtBVz2it7a2Zx2G2t, Model version=gpt-5.5_low |
| FrontierMath Tiers 1-3(v2)Xhigh | Xhigh | 85.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tiers_1_3_v2.csv) CC BY 4.0third-party · Retrieved 2026-11-12 | Run by Epoch AI (third-party measurement). Source label "GPT-5.5 (xhigh)". effort is indicated by the suffix _xhigh in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptfrontiermath_tiers_1_3_v2.csv: Model version=gpt-5.5_xhigh, Best score (across scorers)=0.8526315789473684, stderr=0.021034091168852485, Started at=2026-06-11T17:47:36.000ZLocation frontiermath_tiers_1_3_v2.csv, data row 114 (file line 144), id=5FGXKvXQwGPtcCX2PNrLR5, Model version=gpt-5.5_xhigh |
| FrontierMath Tier 4(v2)Xhigh | Xhigh | 72.5% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0third-party · Retrieved 2026-11-12 | Run by Epoch AI (third-party measurement). Source label "GPT-5.5 (xhigh)". effort is indicated by the suffix _xhigh in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptfrontiermath_tier_4_v2.csv: Model version=gpt-5.5_xhigh, Best score (across scorers)=0.725, stderr=0.07149950690165274, Started at=2026-06-11T17:47:36.000ZLocation frontiermath_tier_4_v2.csv, data row 70 (file line 107), id=PKSMspJiJdNThB6qNvaBSM, Model version=gpt-5.5_xhigh |
| OTIS Mock AIME 2024-2025None | None | 57.8% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, otis_mock_aime_2024_2025.csv) CC BY 4.0third-party · Retrieved 2026-11-12 | Run by Epoch AI (third-party measurement). Source label "GPT-5.5 (no thinking)". effort is indicated by the suffix _none in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptotis_mock_aime_2024_2025.csv: Model version=gpt-5.5_none, Best score (across scorers)=0.5777777777777777, stderr=0.07446027270295805, Started at=2026-08-07T00:53:58.000ZLocation otis_mock_aime_2024_2025.csv, data row 92 (file line 152), id=QuqPmMUTbiEsUvoFYZx5Mk, Model version=gpt-5.5_none |
| OTIS Mock AIME 2024-2025Low | Low | 84.4% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, otis_mock_aime_2024_2025.csv) CC BY 4.0third-party · Retrieved 2026-11-12 | Run by Epoch AI (third-party measurement). Source label "GPT-5.5 (low)". effort is indicated by the suffix _low in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptotis_mock_aime_2024_2025.csv: Model version=gpt-5.5_low, Best score (across scorers)=0.8444444444444444, stderr=0.05463890236888291, Started at=2026-08-07T00:39:05.000ZLocation otis_mock_aime_2024_2025.csv, data row 99 (file line 163), id=CdmtwZ8NR8YeTXWiLVTRDJ, Model version=gpt-5.5_low |
| SimpleQA VerifiedXhigh | Xhigh | 63.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, simpleqa_verified.csv) CC BY 4.0third-party · Retrieved 2026-11-12 | Run by Epoch AI (third-party measurement). Source label "GPT-5.5 (xhigh)". effort is indicated by the suffix _xhigh in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptsimpleqa_verified.csv: Model version=gpt-5.5_xhigh, Best score (across scorers)=0.63, stderr=0.015275252316519465, Started at=2026-08-27T19:28:25.000ZLocation simpleqa_verified.csv, data row 78 (file line 127), id=TijCafTTJUFrJ6jPGvBbgq, Model version=gpt-5.5_xhigh |
| Chess Puzzles(Epoch AI)None | None | 9.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, chess_puzzles.csv) CC BY 4.0third-party · Retrieved 2026-11-12 | Run by Epoch AI (third-party measurement). Source label "GPT-5.5 (no thinking)". effort is indicated by the suffix _none in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptchess_puzzles.csv: Model version=gpt-5.5_none, Best score (across scorers)=0.09, stderr=0.028762349126466143, Started at=2026-10-13T13:53:55.000ZLocation chess_puzzles.csv, data row 81 (file line 132), id=QfS2PrjUFMNnceRZmCmewP, Model version=gpt-5.5_none |
| Chess Puzzles(Epoch AI)Low | Low | 30.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, chess_puzzles.csv) CC BY 4.0third-party · Retrieved 2026-11-12 | Run by Epoch AI (third-party measurement). Source label "GPT-5.5 (low)". effort is indicated by the suffix _low in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptchess_puzzles.csv: Model version=gpt-5.5_low, Best score (across scorers)=0.3, stderr=0.04605661864718382, Started at=2026-10-13T13:54:20.000ZLocation chess_puzzles.csv, data row 80 (file line 131), id=4EayGByBV2xodNBkrZMcFb, Model version=gpt-5.5_low |
| Chess Puzzles(Epoch AI)Xhigh | Xhigh | 63.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, chess_puzzles.csv) CC BY 4.0third-party · Retrieved 2026-11-12 | Run by Epoch AI (third-party measurement). Source label "GPT-5.5 (xhigh)". effort is indicated by the suffix _xhigh in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptchess_puzzles.csv: Model version=gpt-5.5_xhigh, Best score (across scorers)=0.63, stderr=0.048523658709390974, Started at=2026-10-13T13:54:48.000ZLocation chess_puzzles.csv, data row 78 (file line 129), id=DFWQcrbMegFAcEWZKWoJxC, Model version=gpt-5.5_xhigh |
| MirrorCodeHigh | High | 10.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, mirrorcode.csv) CC BY 4.0third-party · Retrieved 2026-11-12 | Run by Epoch AI (third-party measurement). Source label "GPT-5.5 (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptmirrorcode.csv: Model version=gpt-5.5_high, Best score (across scorers)=0.1, stderr=0.06042179781166438, Started at=2026-08-10T16:12:45.865ZLocation mirrorcode.csv, data row 42 (file line 65), id=mirrorcode-ml-2l-gpt-5-5, Model version=gpt-5.5_high |
| MirrorCodeXhigh | Xhigh | 23.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, mirrorcode.csv) CC BY 4.0third-party · Retrieved 2026-11-12 | Run by Epoch AI (third-party measurement). Source label "GPT-5.5 (xhigh)". effort is indicated by the suffix _xhigh in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptmirrorcode.csv: Model version=gpt-5.5_xhigh, Best score (across scorers)=0.23333333333333334, stderr=0.10131411680782823, Started at=2026-10-29T18:03:57.000ZLocation mirrorcode.csv, data row 8 (file line 12), id=Tmy5qo2ScNoA2bapbEG7HP, Model version=gpt-5.5_xhigh |
| Epoch Capabilities Index(ECI)not stated | not stated | 160.1 | — | Epoch AI | Epoch AI, epoch_capabilities_index/eci_scores.csv (CC BY 4.0)third-party · Retrieved 2026-11-12 | A per-model metric that combines results across multiple benchmarks and multiple efforts (not per effort). Calculated by Epoch AI.transcribed from tableSource excerpteci_scores.csv: Model=GPT-5.5, eci=160.1, eci_ci_low=158.12, eci_ci_high=162.36Location epoch_capabilities_index/eci_scores.csv, data row 20 (file line 21), Model=GPT-5.5 |
| τ²-bench banking_knowledge (v1.0.1)Xhigh | Xhigh | 44.6% | — | Sierra | τ²-bench leaderboard submission gpt-5-5_sierra_2026-05-05 (sierra-research/tau2-bench, MIT)third-party · Retrieved 2026-11-13 | τ²-bench leaderboard submission gpt-5-5_sierra_2026-05-05 (submission_type standard, tau2_bench_version 1.0.1). Submitter "Sierra", model_organization "OpenAI": Run by Sierra, which operates τ²-bench (third-party measurement). Verified on the leaderboard (trajectories available, prompts not modified, no questions omitted). The value is pass^1 (%). reasoning_effort "xhigh". User simulator gpt-5.2 (reasoning_effort low). Search configuration retrieval_config "alltools". Evaluation date 2026-07-22. Notes summary: 4 trial runs; seed 300.transcribed from tableSource excerptbanking_knowledge.pass_1=44.58762886597938Location In submissions/gpt-5-5_sierra_2026-05-05/submission.json: results.banking_knowledge.pass_1 (line 17 of file). model_name "GPT-5.5". methodology.notes (line 36) |
Related rankings
- Overall ranking (all models, records)
- GPQA Diamond ranking by metric (all models, records)
- FrontierMath Tiers 1-3(v2) ranking by metric (all models, records)
- FrontierMath Tier 4(v2) ranking by metric (all models, records)
- OTIS Mock AIME 2024-2025 ranking by metric (all models, records)
- SimpleQA Verified ranking by metric (all models, records)
- Chess Puzzles(Epoch AI) ranking by metric (all models, records)
- MirrorCode ranking by metric (all models, records)
- Epoch Capabilities Index(ECI) ranking by metric (all models, records)
- τ²-bench banking_knowledge (v1.0.1) ranking by metric (all models, records)
- Recommendations by role