GPT-5.6 Luna
- Input price
- $0.20
- Per 1 million tokens (USD)
- Output price
- $1.20
- Per 1 million tokens (USD)
- Effort levels
- 6total
- Default: Med
- Benchmark results
- 18total
- Benchmark types: 10
Model information
- API model ID
- gpt-5.6-luna
- release date
- 2026-07-09
- effort
- None / Low / Med (default) / High / Xhigh / Max
- Effort source
- Based on the model page in OpenAI API documentation (developers.openai.com/api/docs/models/gpt-5.6-luna): "Reasoning.effort supports: none, low, medium (default), high, xhigh, and max." (retrieved 2026-11-13)
- Claude Code
- unavailable
- Codex
- unknown
- Availability notes
- 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://developers.openai.com/api/docs/pricing
Price (USD per 1 million tokens)
Prices do not vary by effort; token consumption does.
| input | $0.20 |
|---|---|
| output | $1.20 |
| cache read | $0.02 |
| cache write | $0.25 |
Prompts with more than 272K input tokens are priced at 2x input and cache rates and 1.5x output for the full request. Batch/Flex 50%, Fast 2x. Price reduced by 80% on 2026-07-30
| gpt-5.6-luna | $0.20 | $1.20 | $0.02 | $0.25 | $0.50 | $0.40 | $1.80 | $0.04 | $0.50 | $1.00 |Benchmark results
| Benchmark | effort | Score | Source cost (metric) | measured/reported by | source | Conditions and extraction method |
|---|---|---|---|---|---|---|
| HealthBench Professional (length-adjusted score)not stated | not stated | 55.7 | — | OpenAI | GPT-6 Astra System Card (Table 6. HealthBench Evaluations)official · Retrieved 2026-11-12 | Vendor-reported value. Self-reported by OpenAI. effort not stated. length-adjusted scoretranscribed from tableSource excerpt55.7Location Table 6 "HealthBench Evaluations - reported as length-adjusted score", HealthBench Professional row |
| HealthBench Hard (length-adjusted score)not stated | not stated | 32 | — | OpenAI | GPT-6 Astra System Card (Table 6. HealthBench Evaluations)official · Retrieved 2026-11-12 | Vendor-reported value. Self-reported by OpenAI. effort not stated. length-adjusted scoretranscribed from tableSource excerpt32.0Location Table 6 "HealthBench Evaluations - reported as length-adjusted score", HealthBench Hard row |
| GPQA DiamondNone | None | 63.6% | — | 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-5.6 Luna (none)". 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-5.6-luna_none, Best score (across scorers)=0.6363636363636364, stderr=0.03427308652999934, Started at=2026-08-07T00:35:08.000ZLocation gpqa_diamond.csv, data row 95 (file line 153), id=bDKKx7zTdW5WwMCfwqsLi4, Model version=gpt-5.6-luna_none |
| GPQA DiamondLow | Low | 82.3% | — | 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-5.6 Luna (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-5.6-luna_low, Best score (across scorers)=0.8232323232323232, stderr=0.027178752639044908, Started at=2026-08-07T00:08:31.000ZLocation gpqa_diamond.csv, data row 108 (file line 166), id=nW39ZzuDQ3xTAGVoEfFG95, Model version=gpt-5.6-luna_low |
| GPQA DiamondMax | Max | 91.6% | — | 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-5.6 Luna (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptgpqa_diamond.csv: Model version=gpt-5.6-luna_max, Best score (across scorers)=0.9160353535353535, stderr=0.01728284355494035, Started at=2026-07-09T13:36:49.000ZLocation gpqa_diamond.csv, data row 169 (file line 239), id=LWkDtkmd3TNmLzMhfZD5HW, Model version=gpt-5.6-luna_max |
| FrontierMath Tiers 1-3(v2)None | None | 39.7% | — | 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-5.6 Luna (none)". effort is indicated by the suffix _none in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptfrontiermath_tiers_1_3_v2.csv: Model version=gpt-5.6-luna_none, Best score (across scorers)=0.39649122807017545, stderr=0.029026817016410068, Started at=2026-08-29T11:07:39.000ZLocation frontiermath_tiers_1_3_v2.csv, data row 33 (file line 51), id=YwHKNFQjbat97wVLqachmi, Model version=gpt-5.6-luna_none |
| FrontierMath Tiers 1-3(v2)Low | Low | 41.4% | — | 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-5.6 Luna (low)". effort is indicated by the suffix _low in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptfrontiermath_tiers_1_3_v2.csv: Model version=gpt-5.6-luna_low, Best score (across scorers)=0.41403508771929826, stderr=0.029227738239445765, Started at=2026-08-29T11:07:20.000ZLocation frontiermath_tiers_1_3_v2.csv, data row 35 (file line 53), id=ZryXhNUpPedPvGhbqdNBEw, Model version=gpt-5.6-luna_low |
| FrontierMath Tiers 1-3(v2)Max | Max | 82.1% | — | 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-5.6 Luna (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptfrontiermath_tiers_1_3_v2.csv: Model version=gpt-5.6-luna_max, Best score (across scorers)=0.8210526315789474, stderr=0.02274515950332741, Started at=2026-07-09T14:18:35.000ZLocation frontiermath_tiers_1_3_v2.csv, data row 91 (file line 121), id=YLAk5J3Wd8EruVXee8bAQb, Model version=gpt-5.6-luna_max |
| FrontierMath Tier 4(v2)Max | Max | 61.0% | — | 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-5.6 Luna (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptfrontiermath_tier_4_v2.csv: Model version=gpt-5.6-luna_max, Best score (across scorers)=0.6097560975609756, stderr=0.07712872341874097, Started at=2026-07-09T14:18:35.000ZLocation frontiermath_tier_4_v2.csv, data row 46 (file line 83), id=NLiiJJSyA9wmg2FHENFpAq, Model version=gpt-5.6-luna_max |
| OTIS Mock AIME 2024-2025None | None | 40.0% | — | 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-5.6 Luna (none)". 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-5.6-luna_none, Best score (across scorers)=0.4, stderr=0.07385489458759964, Started at=2026-08-07T00:20:15.000ZLocation otis_mock_aime_2024_2025.csv, data row 105 (file line 170), id=QYZ6wRuT7WMkaYPKc9dRPy, Model version=gpt-5.6-luna_none |
| OTIS Mock AIME 2024-2025Low | Low | 66.7% | — | 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-5.6 Luna (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-5.6-luna_low, Best score (across scorers)=0.6666666666666666, stderr=0.07106690545187014, Started at=2026-08-07T00:02:15.000ZLocation otis_mock_aime_2024_2025.csv, data row 121 (file line 186), id=ZgU8BagFmaj7BE94y3JDZA, Model version=gpt-5.6-luna_low |
| OTIS Mock AIME 2024-2025Max | Max | 98.3% | — | 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-5.6 Luna (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptotis_mock_aime_2024_2025.csv: Model version=gpt-5.6-luna_max, Best score (across scorers)=0.9833333333333333, stderr=0.011650421590325524, Started at=2026-07-09T13:36:49.000ZLocation otis_mock_aime_2024_2025.csv, data row 177 (file line 252), id=AhtQ5ggs4pTfLDqHFjueGy, Model version=gpt-5.6-luna_max |
| SimpleQA VerifiedMax | Max | 41.0% | — | 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-5.6 Luna (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptsimpleqa_verified.csv: Model version=gpt-5.6-luna_max, Best score (across scorers)=0.41, stderr=0.015560917136921657, Started at=2026-08-10T23:44:20.000ZLocation simpleqa_verified.csv, data row 94 (file line 144), id=CeDghdBk8CqtiFSbUzxNH5, Model version=gpt-5.6-luna_max |
| Chess Puzzles(Epoch AI)None | None | 3.0% | — | 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-5.6 Luna (none)". 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-5.6-luna_none, Best score (across scorers)=0.03, stderr=0.01714466079977653, Started at=2026-10-13T13:53:29.000ZLocation chess_puzzles.csv, data row 84 (file line 135), id=5Q7zWYmoRik8mhABL4wpVR, Model version=gpt-5.6-luna_none |
| Chess Puzzles(Epoch AI)Low | Low | 17.0% | — | 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-5.6 Luna (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-5.6-luna_low, Best score (across scorers)=0.17, stderr=0.03775251680686369, Started at=2026-10-13T13:53:37.000ZLocation chess_puzzles.csv, data row 83 (file line 134), id=FagAUZ7m5PJHseDATvp2vf, Model version=gpt-5.6-luna_low |
| Chess Puzzles(Epoch AI)Max | Max | 43.0% | — | 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-5.6 Luna (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptchess_puzzles.csv: Model version=gpt-5.6-luna_max, Best score (across scorers)=0.43, stderr=0.0497569851956243, Started at=2026-10-13T13:53:45.000ZLocation chess_puzzles.csv, data row 82 (file line 133), id=LUfGWqWQim7rdBPgSpbrXS, Model version=gpt-5.6-luna_max |
| MirrorCodeMax | Max | 21.1% | — | 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-5.6 Luna (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptmirrorcode.csv: Model version=gpt-5.6-luna_max, Best score (across scorers)=0.2111111111111111, stderr=0.09822049844066655, Started at=2026-10-21T16:48:59.000ZLocation mirrorcode.csv, data row 14 (file line 19), id=XwpZADrRSwBo2pETMdLVRq, Model version=gpt-5.6-luna_max |
| Epoch Capabilities Index(ECI)not stated | not stated | 156.67 | — | 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-5.6 Luna, eci=156.67, eci_ci_low=154.83, eci_ci_high=158.69Location epoch_capabilities_index/eci_scores.csv, data row 35 (file line 36), Model=GPT-5.6 Luna |
Related rankings
- Overall ranking (all models, records)
- HealthBench Professional (length-adjusted score) ranking by metric (all models, records)
- HealthBench Hard (length-adjusted score) ranking by metric (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)
- Recommendations by role