Grok 4.7
- Input price
- $2.00
- Per 1 million tokens (USD)
- Output price
- $6.00
- Per 1 million tokens (USD)
- Effort levels
- 4total
- Default: High
- Benchmark results
- 15total
- Benchmark types: 15
Model information
- API model ID
- grok-4.7
- release date
- 2026-09-21
- effort
- Low / Med / High (default) / Xhigh
- Effort source
- Based on xAI reasoning documentation (docs.x.ai/docs/guides/reasoning).
- Claude Code
- unavailable
- Codex
- unavailable
- Availability notes
- Official statements about Claude Code / Codex support have not been confirmed. The official model list for Claude Code / Codex (checked 2026-11-12) contains only Anthropic / OpenAI models, respectively, so both are false.
- Availability source
- https://docs.x.ai/docs/models
Price (USD per 1 million tokens)
Prices do not vary by effort; token consumption does.
| input | $2.00 |
|---|---|
| output | $6.00 |
| cache read | $0.50 |
| cache write | — |
For prompts of 200k or more, the entire request is input $4.00 / cached $1.00 / output $12.00. context 500k. The Fast version runs at 2x the speed and costs 2x as much (announcement page)
grok-4.7 500k <200k prompt tokens $2.00 $0.50 $6.00 / ≥200k $4.00 $1.00 $12.00Source: https://docs.x.ai/docs/models
Benchmark results
| Benchmark | effort | Score | Source cost (metric) | measured/reported by | source | Conditions and extraction method |
|---|---|---|---|---|---|---|
| Terminal-Bench 4.0Xhigh | Xhigh | 37.6% | — | xAI | Grok 4.7 (xAI news)official · Retrieved 2026-11-12 | Vendor-reported value. Self-reported by xAI. Table heading is Grok 4.7 (xHigh)transcribed from tableSource excerptTerminal-Bench 4.0 | Grok 4.7 (xHigh) 37.6 |
| CursorBench 4.0Xhigh | Xhigh | 46.3% | — | xAI | Grok 4.7 (xAI news)official · Retrieved 2026-11-12 | Vendor-reported value. Self-reported by xAI. Table heading is Grok 4.7 (xHigh)transcribed from tableSource excerptCursorBench 4.0 | Grok 4.7 (xHigh) 46.3 |
| DeepSWE v1.1High (default) | High | 71.0% | — | xAI | Grok 4.7 (xAI news)official · Retrieved 2026-11-12 | Vendor-reported value. Self-reported by xAI. Table heading is Grok 4.7 (xHigh). A footnote states that DeepSWE is a high effort valuetranscribed from tableSource excerptDeepSWE v1.1 | Grok 4.7 (xHigh) 71.0(footnote: high effort) |
| AA-Briefcase v1.1(Elo)Xhigh | Xhigh | 1,657 | — | xAI | Grok 4.7 (xAI news)official · Retrieved 2026-11-12 | Vendor-reported value. Self-reported by xAI. Table heading is Grok 4.7 (xHigh)transcribed from tableSource excerptAA Briefcase v1.1 | Grok 4.7 (xHigh) 1657 |
| HealthBench ProfessionalXhigh | Xhigh | 56.7% | — | xAI | Grok 4.7 (xAI news)official · Retrieved 2026-11-12 | Vendor-reported value. Self-reported by xAI. Table heading is Grok 4.7 (xHigh)transcribed from tableSource excerptHealthBench Professional | Grok 4.7 (xHigh) 56.7 |
| Harvey Legal Agent BenchmarkXhigh | Xhigh | 19.6% | — | xAI | Grok 4.7 (xAI news)official · Retrieved 2026-11-12 | Vendor-reported value. Self-reported by xAI. Table heading is Grok 4.7 (xHigh)transcribed from tableSource excerptHarvey Legal Agent Benchmark | Grok 4.7 (xHigh) 19.6 |
| EEBenchXhigh | Xhigh | 64.0% | — | xAI | Grok 4.7 (xAI news)official · Retrieved 2026-11-12 | Vendor-reported value. Self-reported by xAI. Table heading is Grok 4.7 (xHigh)transcribed from tableSource excerptEEBench | Grok 4.7 (xHigh) 64.0 |
| GPQA DiamondXhigh | Xhigh | 92.7% | — | 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 "Grok 4.7 (xhigh)". effort is indicated by the suffix _xhigh in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptgpqa_diamond.csv: Model version=grok-4.7_xhigh, Best score (across scorers)=0.92739898989899, stderr=0.015505824295534454, Started at=2026-09-22T21:49:22.000ZLocation gpqa_diamond.csv, data row 21 (file line 45), id=hxAhYJfXdPNanxatXpG5hC, Model version=grok-4.7_xhigh |
| FrontierMath Tiers 1-3(v2)Xhigh | Xhigh | 53.0% | — | 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 "Grok 4.7 (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=grok-4.7_xhigh, Best score (across scorers)=0.5298245614035088, stderr=0.029616712041900365, Started at=2026-09-22T21:49:22.000ZLocation frontiermath_tiers_1_3_v2.csv, data row 15 (file line 28), id=F4unBbW5M4VJogzCq4vGAb, Model version=grok-4.7_xhigh |
| FrontierMath Tier 4(v2)Xhigh | Xhigh | 17.1% | — | 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 "Grok 4.7 (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=grok-4.7_xhigh, Best score (across scorers)=0.17073170731707318, stderr=0.05949419959829495, Started at=2026-09-22T21:49:22.000ZLocation frontiermath_tier_4_v2.csv, data row 15 (file line 28), id=Ymgj5VeEceBbzsLq6xEZRi, Model version=grok-4.7_xhigh |
| OTIS Mock AIME 2024-2025Xhigh | Xhigh | 98.1% | — | 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 "Grok 4.7 (xhigh)". effort is indicated by the suffix _xhigh in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptotis_mock_aime_2024_2025.csv: Model version=grok-4.7_xhigh, Best score (across scorers)=0.9805555555555555, stderr=0.014299486306926387, Started at=2026-09-22T21:49:22.000ZLocation otis_mock_aime_2024_2025.csv, data row 23 (file line 47), id=Jhgwm7QpspGcvm7DUVqUDg, Model version=grok-4.7_xhigh |
| SimpleQA VerifiedXhigh | Xhigh | 56.0% | — | 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 "Grok 4.7 (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=grok-4.7_xhigh, Best score (across scorers)=0.56, stderr=0.015704987954361718, Started at=2026-09-22T21:49:22.000ZLocation simpleqa_verified.csv, data row 21 (file line 45), id=6izDCw5ygCLZJEKPS8jV5T, Model version=grok-4.7_xhigh |
| Chess Puzzles(Epoch AI)Xhigh | Xhigh | 41.0% | — | 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 "Grok 4.7 (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=grok-4.7_xhigh, Best score (across scorers)=0.41, stderr=0.04943110704237103, Started at=2026-10-13T12:39:21.000ZLocation chess_puzzles.csv, data row 162 (file line 219), id=L5Ck7pMy8bVmVMMLwxJN7f, Model version=grok-4.7_xhigh |
| MirrorCodeXhigh | Xhigh | 54.4% | — | 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 "Grok 4.7 (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=grok-4.7_xhigh, Best score (across scorers)=0.5444444444444444, stderr=0.11439589045541113, Started at=2026-10-29T18:04:16.000ZLocation mirrorcode.csv, data row 5 (file line 6), id=2CP56MmAkTeFXXT8pSGre4, Model version=grok-4.7_xhigh |
| Epoch Capabilities Index(ECI)not stated | not stated | 156.18 | — | 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=Grok 4.7, eci=156.18, eci_ci_low=154.23, eci_ci_high=158.27Location epoch_capabilities_index/eci_scores.csv, data row 38 (file line 39), Model=Grok 4.7 |
Related rankings
- Overall ranking (all models, records)
- Terminal-Bench 4.0 ranking by metric (all models, records)
- CursorBench 4.0 ranking by metric (all models, records)
- DeepSWE v1.1 ranking by metric (all models, records)
- AA-Briefcase v1.1(Elo) ranking by metric (all models, records)
- HealthBench Professional ranking by metric (all models, records)
- Harvey Legal Agent Benchmark ranking by metric (all models, records)
- EEBench 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