SpaceXAIReasoning modelGrok 4.7
Grok 4.7 is a SpaceXAI proprietary reasoning model, released 21 Sept 2026. Its best configuration (high reasoning effort) ranks #61 of 756 on the BenchLeader Index at 63.6 ±6.0, in the upper half. The ± is the point: 169 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in composite (83) and lowest in long context (64). At $3.00 per million tokens blended it is pricier than most ranked models. Output speed of 78 tokens per second puts it slower than most, with a first answer in 33.1 s. It has been measured at 5 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 21 Sept 2026.
- Blended price
- $3.00/M
- $2.00 in · $6.00 out
- Output speed
- 78 tok/s
- measured by Artificial Analysis
- First answer
- 33 s
- first token 2.24 s
- Context
- 500k
- Full answer
- 39 s
- median, reasoning included
- Cost per run
- $2.73
- one full Intelligence Index run
- Released
- 21 Sept 2026
- Overall index64
- Reasoning72
- Coding65
- Knowledge76
- Long context64
- Composite83
Versions
SpaceXAI has shipped 9 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| low | 61.7 | #91 | 78 tok/s | 8.92 s | $0.0026 | Coding 62 · Composite 78 · Knowledge 75 · Long context 65 · Multimodal 61 · Reasoning 64 |
| medium | – | – | 64 tok/s | 2.24 s | $0.0026 | |
| highbest | 63.6 | #61 | 78 tok/s | 33 s | $0.0026 | Coding 65 · Composite 83 · Knowledge 76 · Long context 64 · Reasoning 72 |
| xhigh | 61.1 | #96 | 81 tok/s | 49 s | $0.0026 | Agents & tools 52 · Coding 63 · Composite 70 · Human preference 63 · Knowledge 66 · Long context 64 · Maths 57 · Reasoning 68 |
| not stated | – | – | 64 tok/s | 2.24 s | $0.0026 | Agents & tools 54 · Coding 62 · Maths 47 |
What more thinking costs
Turning the effort up buys index points and multiplies the bill. Here xhigh costs 3.0× low for -0.6 on the index — -0.4 points per doubling of spend. Compare that with other models.
How its index has moved
21 Sept 2026 to 3 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | low | medium | high | xhigh | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|
| GPQA Diamond | – | – | – | 92.7%#23 | – | Epoch AI Benchmarking Hub | |
| LMArena Hard Prompts | – | – | – | 1462#90 | – | LMArena | |
| LiveBench Reasoningnot in index | – | – | – | 82.7%#44 | – | LiveBench | |
| Humanity's Last Exam (AA)not in index | 39.2%#85 | – | 42.3%#62 | 43.1%#53 | – | Artificial Analysis | |
| CritPt | 13.4%#90 | – | 18.0%#63 | 17.7%#65 | – | Artificial Analysis | |
| MysteryMechanismnot in index | – | – | – | 25.2%#13 | – | Vals AI | |
| Chess Puzzlesnot in index | – | – | – | 38.0%#32 | – | Epoch AI Benchmarking Hub | |
| Mystery Game Puzzlesnot in index | – | – | – | 29.0%#31 | – | Epoch AI Benchmarking Hub | |
| LMCAnot in index | – | – | – | 49.4%#54 | – | Epoch AI Benchmarking Hub | |
| DTBenchnot in index | – | – | – | 96.0%#22 | – | Epoch AI Benchmarking Hub |
Coding
| Benchmark | low | medium | high | xhigh | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|
| SciCode | 54.9%#50 | – | 57.8%#22 | 57.4%#25 | – | SciCode | |
| FrontierCode | – | – | – | – | 47.6%#11 | Cognition | |
| LMArena Coding | – | – | – | 1488#93 | – | LMArena | |
| LMArena WebDev | – | – | – | 1638#15 | – | LMArena | |
| LiveBench Codingnot in index | – | – | – | 77.2%#37 | – | LiveBench | |
| SciCode (AA)not in index | 54.9%#53 | – | 57.8%#21 | 57.4%#24 | – | Artificial Analysis | |
| IOI | – | – | – | 57.7%#15 | – | Vals AI | |
| Code Migrationnot in index | – | – | – | 44.8%#16 | – | Vals AI | |
| ProgramBenchnot in index | – | – | – | 0.5%#13 | – | Vals AI | |
| Vibe Code Bench v1.1not in index | – | – | – | 86.2%#10 | – | Vals AI | |
| CursorBenchnot in index | 33.1%#44 | 41.6%#22 | 43.9%#17 | 46.3%#13 | – | Cursor | |
| FrontierSWEnot in index | – | – | – | 29.5%#10 | – | Epoch AI Benchmarking Hub | |
| Terminal-Bench 4.0 (AA)not in index | 16.2%#59 | – | 24.8%#47 | 25.8%#45 | – | Artificial Analysis |
Agents & tools
| Benchmark | low | medium | high | xhigh | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|
| Terminal-Bench | – | – | – | 37.6%#45 | – | Terminal-Bench | |
| APEX-Agents | – | – | – | – | 54.6%#20 | Mercor | |
| LMArena Agent | – | – | – | 4#16 | – | LMArena | |
| LiveBench Agentic Codingnot in index | – | – | – | 54.0%#31 | – | LiveBench | |
| Terminal-Bench 2.1 (Vals) | – | – | – | 73.4%#22 | – | Vals AI | |
| GDPval (AA)not in index | 53.7%#32 | – | 60.5%#7 | 59.8%#9 | – | Artificial Analysis | |
| ITBench SRE (AA)not in index | – | – | – | 42.1%#16 | – | Artificial Analysis | |
| CyberBenchnot in index | – | – | – | 69.5%#21 | – | Vals AI | |
| Finance Agent v2not in index | – | – | – | 52.3%#29 | – | Vals AI | |
| Harvey's Legal Agent Benchmarknot in index | – | – | – | 12.5%#8 | – | Vals AI | |
| Legal Research Benchnot in index | – | – | – | 47.1%#12 | – | Vals AI | |
| Tax Agent Benchnot in index | – | – | – | 65.6%#16 | – | Vals AI | |
| Terminal-Bench 4.0 (Vals)not in index | – | – | – | 28.8%#14 | – | Vals AI | |
| Terminal-Bench Sciencenot in index | – | – | – | 10.0%#11 | – | Vals AI | |
| Vending-Bench 2not in index | – | – | – | – | 10536.8#6 | Andon Labs | |
| AutomationBenchnot in index | – | – | – | 65.6%#11 | – | Artificial Analysis | |
| GDP.pdfnot in index | – | – | – | 20.0%#27 | – | Artificial Analysis | |
| AA-Briefcasenot in index | – | – | – | 1644#9 | – | Artificial Analysis |
Maths
| Benchmark | low | medium | high | xhigh | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|
| FrontierMath Tiers 1–3 | – | – | – | 53.0%#45 | – | Epoch AI Benchmarking Hub | |
| FrontierMath Tier 4 | – | – | – | 17.1%#49 | – | Epoch AI Benchmarking Hub | |
| OTIS Mock AIME | – | – | – | 98.1%#22 | – | Epoch AI Benchmarking Hub | |
| ProofBench | – | – | – | – | 34.0%#40 | Vals AI | |
| LiveBench Mathematicsnot in index | – | – | – | 95.7%#15 | – | LiveBench | |
| LMArena Maths | – | – | – | 1444#79 | – | LMArena |
Knowledge
| Benchmark | low | medium | high | xhigh | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|
| SimpleQA Verified | – | – | – | 56.0%#18 | – | Epoch AI Benchmarking Hub | |
| LiveBench Data Analysisnot in index | – | – | – | 76.9%#29 | – | LiveBench | |
| AA-Omniscience | 29.6#32 | – | 30.9#30 | 32.0#27 | – | Artificial Analysis | |
| LegalBench | – | – | – | 84.4%#31 | – | Vals AI | |
| PRBench Legal | – | – | – | 47.6%#15 | – | Scale AI SEAL | |
| BioMysteryBenchnot in index | – | – | – | 69.3%#11 | – | Vals AI | |
| Excel Modeling Benchmarknot in index | – | – | – | 67.0%#17 | – | Vals AI | |
| MedCodenot in index | – | – | – | 49.5%#20 | – | Vals AI | |
| MedScribenot in index | – | – | – | 89.4%#6 | – | Vals AI | |
| Public Benefits Benchnot in index | – | – | – | 65.6%#17 | – | Vals AI | |
| GDP.pdfnot in index | – | – | – | 22.8%#22 | – | Epoch AI Benchmarking Hub | |
| AA-Omniscience: accuracynot in index | 49.7%#62 | – | 47.8%#72 | 47.5%#74 | – | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 60.1%#70 | – | 67.6%#51 | 70.7%#36 | – | Artificial Analysis |
Instruction following
| Benchmark | low | medium | high | xhigh | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|
| LiveBench Languagenot in index | – | – | – | 80.1%#29 | – | LiveBench | |
| LiveBench Instruction Followingnot in index | – | – | – | 75.3%#10 | – | LiveBench | |
| LMArena Instruction Followingnot in index | – | – | – | 1440#78 | – | LMArena |
Human preference
| Benchmark | low | medium | high | xhigh | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|
| LMArena Text | – | – | – | 1443#89 | – | LMArena | |
| LMArena Creative Writingnot in index | – | – | – | 1436#63 | – | LMArena | |
| LMArena Multi-turnnot in index | – | – | – | 1433#105 | – | LMArena | |
| LMArena Longer Queriesnot in index | – | – | – | 1453#83 | – | LMArena |
Multimodal
| Benchmark | low | medium | high | xhigh | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|
| MMMU-Pro | 78.2%#72 | – | – | – | – | Artificial Analysis | |
| SAGEnot in index | – | – | – | 40.8%#57 | – | Vals AI | |
| Blueprint-Bench 2not in index | – | – | – | – | 32.5%#12 | Epoch AI Benchmarking Hub |
Long context
| Benchmark | low | medium | high | xhigh | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|
| AA-LCR | 80.0%#70 | – | 77.0%#124 | 76.7%#126 | – | Artificial Analysis | |
| MLCRnot in index | – | – | – | 15.0%#27 | – | Artificial Analysis |
Composite
| Benchmark | low | medium | high | xhigh | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|
| LiveBench | – | – | – | 77.4%#24 | – | LiveBench | |
| AA Intelligence Index | 42.2#47 | – | 46.3#30 | 46.5#29 | – | Artificial Analysis | |
| Vals Indexnot in index | – | – | – | 55.0#14 | – | Vals AI |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| SpaceXAI | 64 tok/s | 0.83 s | $2.20 | $6.60 | 500k | – |
| SpaceXAI | 59 tok/s | 3.32 s | $2.00 | $6.00 | 500k | – |
| SpaceXAI | 52 tok/s | 3.08 s | $2.00 | $6.00 | 500k | – |
Price history
Listed price per 1M tokens over time, as recorded by OpenRouter for the provider with the longest history.
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.500 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0026 | $0.0022 | 36.9 s |
| Summarise a 30-page report | 12,000 / 600 | $0.028 | $0.014 | 40.8 s |
| Code edit | 6,000 / 1,500 | $0.021 | $0.014 | 52.3 s |
| Agentic coding session | 60,000 / 4,000 | $0.144 | $0.076 | 1.4 min |
| Structured extraction | 2,000 / 200 | $0.0052 | $0.0030 | 35.7 s |
See also
Data as of 5 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “Grok 4.7: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/grok-4-7, data as of 5 Oct 2026.