Grok 4.7 vs Qwen3.6 Max
Full profiles: Grok 4.7 (SpaceXAI) and Qwen3.6 Max (Alibaba): every benchmark, price and rank.
Updated · Data from 12 sources
As of 16 Nov 2026, Qwen3.6 Max is ahead of Grok 4.7 on quality (62.1 vs 57.4 on the BenchLeader Index), and they cost about the same at $3.00 vs $2.92 per 1M tokens blended. Choose Grok 4.7 for coding (61 vs 56); choose Qwen3.6 Max for agents & tools (72 vs 57), maths (64 vs 56), and reasoning (61 vs 56).
Key facts (as of 16 Nov 2026)
- Grok 4.7 scores 57.4 on the BenchLeader Index and Qwen3.6 Max scores 62.1 (BenchLeader, 16 Nov 2026).
- Grok 4.7 costs $3.00 per 1M tokens blended (list price, 16 Nov 2026).
- Qwen3.6 Max costs $2.92 per 1M tokens blended (list price, 16 Nov 2026).
- On Arena WebDev, Grok 4.7 is rated 1641 and Qwen3.6 Max 1482 (LMArena, as published by 16 Nov 2026).
Which to pick for…
The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.
| Use case | Pick | Why | Confidence |
|---|---|---|---|
| Coding | Grok 4.7 | 61 vs 56 category score; Arena WebDev 1641 vs 1482 | Medium |
| Agents & tool use | Qwen3.6 Max | 72 vs 57 category score | High |
| Maths | Qwen3.6 Max | 64 vs 56 category score; Arena Maths 1471 vs 1447 | High |
| Reasoning | Qwen3.6 Max | 61 vs 56 category score; Arena Hard Prompts 1481 vs 1466 | Medium |
| Knowledge | Either | 60 vs 60 category score; SimpleQA Verified 56.0% vs 52.0% | Either |
| Long documents | Qwen3.6 Max | 65 vs 63 category score; AA-LCR v1.1 80.7% vs 76.7% | Medium |
| Chat quality (human preference) | Qwen3.6 Max | 65 vs 63 on Arena votes | Medium |
| Lowest cost | Either | $3.00 vs $2.92 per 1M blended; agentic coding session $0.144 vs $0.109 | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- Qwen3.6 Max (max) leads on quality: 62.1 vs 57.4.
- Grok 4.7 (xhigh) is stronger in coding, knowledge.
- Qwen3.6 Max (max) is stronger in agents & tools, human preference, long context, maths, reasoning.
- They cost about the same ($2.92 per 1M blended).
At a glance
| Spec | Grok 4.7 | Qwen3.6 Max |
|---|---|---|
| Developer | SpaceXAI | Alibaba |
| Released | 21 Sep 2026 | 20 Apr 2026 |
| Context window (tokens) | 500,000 | 262,144 |
| Compared at | Grok 4.7 (xhigh) | Qwen3.6 Max (max) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $2.00 / $6.00 / $0.500 | $1.30 / $7.80 / $0.130 |
Category by category
Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.
| Category | Grok 4.7 (xhigh) | Qwen3.6 Max (max) | Leader |
|---|---|---|---|
| Reasoning | 55.6 | 60.8 | Qwen3.6 Max |
| Coding | 60.9 | 55.9 | Grok 4.7 |
| Agents & tools | 56.9 | 72.1 | Qwen3.6 Max |
| Maths | 55.8 | 64.4 | Qwen3.6 Max |
| Knowledge | 59.9 | 59.7 | level |
| Instruction following | – | 74.7 | not comparable |
| Human preference | 62.5 | 64.5 | Qwen3.6 Max |
| Multimodal | 55.5 | – | not comparable |
| Long context | 62.9 | 65.0 | Qwen3.6 Max |
| Composite | 52.8 | – | not comparable |
On one chart
Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.
Not drawn, measured for fewer than two of these models: Instruction following, Multimodal.
Where sources disagree
Across the 18 benchmarks both have, Grok 4.7 leads 9, Qwen3.6 Max leads 9. Every overall index that rates both puts Qwen3.6 Max ahead.
| Overall index | Grok 4.7 (xhigh) | Qwen3.6 Max (max) | Leader |
|---|---|---|---|
| BenchLeader Index | 57.4 | 62.1 | Qwen3.6 Max |
| Arena Text | 1443 | 1460 | Qwen3.6 Max |
Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).
Price, speed and latency
List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | Grok 4.7 (xhigh) | Qwen3.6 Max (max) |
|---|---|---|
| Blended price per 1M tokens | $3.00 | $2.92 |
| Input / output per 1M | $2.00 / $6.00 | $1.30 / $7.80 |
| Cached input per 1M | $0.500 | $0.130 |
| Price per task: chat reply | $0.0026 | $0.0029 |
| Price per task: summarize a 30-page report | $0.028 | $0.020 |
| Price per task: code edit | $0.021 | $0.019 |
| Price per task: agentic coding session | $0.144 | $0.109 |
| Price per task: structured extraction | $0.0052 | $0.0042 |
| Agentic coding session, input mostly cached | $0.076 | $0.057 |
| Cost per benchmark task (AA Index) | $7.77 | – |
| Output tokens per task (AA Index) | 105k | – |
| Of which reasoning | 69k | – |
| Time per task (AA Index) | 26 min | – |
| Output speed | 68 tok/s | – |
| Time to first answer | 55.9 s | – |
| Time to a complete answer, last measured 13 Nov 2026 | 145.5 s | – |
Each model is compared at its best-ranked reasoning-effort setting. Grok 4.7 (xhigh) scores 57.4 and takes 56 s to its first answer token; Grok 4.7 (high) scores 56.9 in 35 s, Grok 4.7 (low) scores 55.4 in 10 s. Qwen3.6 Max (max) scores 62.1. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.
Every benchmark
157 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.
| Metric | Publisher | Grok 4.7 (xhigh) | Qwen3.6 Max (max) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 57.4 | 62.1 |
| Agents & tools score | BenchLeader | 56.9 | 72.1 |
| Coding score | BenchLeader | 60.9 | 55.9 |
| Composite score | BenchLeader | 52.8 | – |
| Human preference score | BenchLeader | 62.5 | 64.5 |
| Knowledge score | BenchLeader | 59.9 | 59.7 |
| Long context score | BenchLeader | 62.9 | 65.0 |
| Maths score | BenchLeader | 55.8 | 64.4 |
| Multimodal score | BenchLeader | 55.5 | – |
| Reasoning score | BenchLeader | 55.6 | 60.8 |
| Instruction following score | BenchLeader | – | 74.7 |
| Blended price $/M | BenchLeader | $3.00 | $2.92 |
| Output speed | BenchLeader | 68 tok/s | – |
| Time to first answer | BenchLeader | 55.9 s | – |
| Context window | BenchLeader | 500,000 tokens | 262,144 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 92.7% | 87.4% |
| SimpleBench | SimpleBench | – | 63.0% |
| Arena Hard Prompts | Arena (LMArena) | 1466 | 1481 |
| LiveBench 2.0 Reasoning | LiveBench | 82.7% | – |
| LiveBench 1.0 Reasoning | LiveBench | 82.7% | – |
| GPQA Diamond (AA) | Artificial Analysis | – | 88.8% |
| Humanity's Last Exam (AA) | Artificial Analysis | 43.1% | 30.8% |
| HLE-Diamond (AA) | Artificial Analysis | 23.2% | – |
| ARC-AGI-1 | ARC Prize | 89.5% | – |
| ARC-AGI-2 | ARC Prize | 61.4% | – |
| ARC-AGI-3 | ARC Prize | 7.0% | – |
| CritPt | Artificial Analysis | 17.7% | 3.7% |
| CritPt v2 hard subset (AA) | Artificial Analysis | 33.5% | – |
| MysteryMechanism | Vals AI | 25.2% | – |
| HLE-Diamond (Scale) | Scale AI SEAL | 23.4%† | – |
| Arena Expert | Arena (LMArena) | 1478 | 1497 |
| Chess Puzzles | Epoch AI Benchmarking Hub | 41.0% | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 29.0% | 19.0%† |
| LMCA | Epoch AI Benchmarking Hub | 49.4% | 42.5% |
| DTBench | Epoch AI Benchmarking Hub | 96.0% | 87.2% |
| Coding | |||
| SWE-bench Verified (Epoch) | Epoch AI Benchmarking Hub | – | 76.7% |
| SciCode | SciCode | 57.4% | – |
| FrontierCode | Cognition | 47.6%† | – |
| Arena Coding | Arena (LMArena) | 1493 | 1510 |
| Arena WebDev | Arena (LMArena) | 1641 | 1482 |
Show all 157 benchmarks
| Metric | Publisher | Grok 4.7 (xhigh) | Qwen3.6 Max (max) |
|---|---|---|---|
| Coding | |||
| LiveBench 2.0 Coding | LiveBench | 73.1% | – |
| LiveBench 1.0 Coding | LiveBench | 77.2% | – |
| IOI | Vals AI | 57.7% | – |
| SWE-bench (Vals) | Vals AI | – | 72.8% |
| Code Migration | Vals AI | 44.8% | – |
| Code Migration v1.1 | Vals AI | 53.2% | – |
| ProgramBench | Vals AI | 0.5% | – |
| SWE-bench Multimodal | Vals AI | 42.9% | – |
| Vibe Code Bench v1.1 | Vals AI | 86.2% | – |
| Vibe Code Bench 1-100 v1.1 | Vals AI | 26.4% | – |
| SWE Atlas v1.1 | Scale AI SEAL | 62.1%† | – |
| SWE Atlas v1.1: Codebase QnA | Scale AI SEAL | 73.4%† | – |
| SWE Atlas v1.1: Test Writing | Scale AI SEAL | 64.4%† | – |
| SWE Atlas v1.1: Refactoring | Scale AI SEAL | 48.6%† | – |
| MirrorCode | Epoch AI Benchmarking Hub | 54.4% | – |
| CursorBench | Cursor | 46.3% | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 1545.8 | – |
| FrontierSWE | Epoch AI Benchmarking Hub | 29.5% | – |
| WeirdML v3 | WeirdML | 8.4% | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 25.8% | – |
| Startrise Frontend | Startrise | 75.9%† | – |
| GameBench 2 Overall | DuelLab GameBench 2 | 63.6† | – |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 71.2 | – |
| Design Arena Website | Design Arena | 1244† | – |
| FrontierCode 1.1 (AA) | Artificial Analysis | 33.8% | – |
| FrontierCode 2.0 (AA) | Artificial Analysis | 28.7% | – |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 38.8% | – |
| APEX-Agents | Mercor | 54.6%† | – |
| Arena Agent | Arena (LMArena) | 2.6 | – |
| LiveBench Long Agentic | LiveBench | 45.3% | – |
| LiveBench Browser | LiveBench | 49.3% | – |
| LiveBench Agentic Coding | LiveBench | 54.0% | – |
| Terminal-Bench Hard | Artificial Analysis | – | 43.9% |
| τ²-Bench Telecom (AA) | Artificial Analysis | – | 95.9% |
| Terminal-Bench 2.1 (Vals) | Vals AI | 73.4% | – |
| GDPval-AA v2.1, normalised score | Artificial Analysis | 60.7% | – |
| GDPval-AA v2.1 | Artificial Analysis | 1717 | – |
| ITBench SRE (AA) | Artificial Analysis | 42.1% | – |
| Analyst Agent (AA) | Artificial Analysis | 52.5% | – |
| CyberBench | Vals AI | 69.5% | – |
| Finance Agent v2 | Vals AI | 52.3% | – |
| Finance Agent v2.1 | Vals AI | 60.6% | – |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 18.3% | – |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 12.5% | – |
| Legal Research Bench | Vals AI | 47.1% | – |
| Robo-bench | Vals AI | 0.2% | – |
| SREBench | Vals AI | 3.8% | – |
| Tax Agent Bench | Vals AI | 35.8% | – |
| Terminal-Bench 2.0 (Vals) | Vals AI | – | 51.7% |
| Terminal-Bench 4.0 (Vals) | Vals AI | 28.8% | – |
| Terminal-Bench Science | Vals AI | 10.0% | – |
| Arena Agent Task Completion | Arena (LMArena) | 5.1 | – |
| Vending-Bench 2 | Andon Labs | 10536.8† | 4254.2 |
| AutomationBench | Artificial Analysis | 65.6% | – |
| GDP.pdf (AA) | Artificial Analysis | 20.0% | – |
| Harvey LAB-AA v1.1 | Harvey | 9.4% | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1636 | – |
| GDPx | GDPx by SemiAnalysis | 3.9% | – |
| Design Arena Agentic | Design Arena | 1277† | – |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 11.4% | – |
| CWE-Bench (AA) | Artificial Analysis | 68.3% | – |
| DeepSec-Bench (AA) | Artificial Analysis | 26.9% | – |
| CyberGym end-to-end (AA) | Artificial Analysis | 74.0% | – |
| MKA (AA) | Artificial Analysis | 40.1% | – |
| FACTS Search | 85.6%† | – | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 53.0% | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 17.1% | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 98.1% | 91.1% |
| ProofBench | Vals AI | 26.0%† | – |
| LiveBench Mathematics | LiveBench | 95.7% | – |
| Arena Maths | Arena (LMArena) | 1447 | 1471 |
| FrontierMath Erdős | Epoch AI Benchmarking Hub | 0.0% | – |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 56.0% | 52.0% |
| LiveBench 2.0 Data Analysis | LiveBench | 76.9% | – |
| LiveBench Research | LiveBench | 89.5% | – |
| LiveBench 1.0 Data Analysis | LiveBench | 76.9% | – |
| AA-Omniscience v1.1 | Artificial Analysis | 31.2 | – |
| LegalBench | Vals AI | 84.4% | – |
| CorpFin | Vals AI | – | 66.5% |
| PRBench Legal | Scale AI SEAL | 47.6% | – |
| BioMysteryBench | Vals AI | 69.3% | – |
| CaseLaw v2 | Vals AI | – | 47.9% |
| Excel Modeling Benchmark | Vals AI | 67.0% | – |
| Excel Modeling Benchmark v1.1 | Vals AI | 71.5% | – |
| MedCode | Vals AI | 49.5% | – |
| MedScribe | Vals AI | 89.4% | – |
| Public Benefits Bench v1.1 | Vals AI | 65.6% | – |
| Access to Justice Benchmark | Vals AI | 73.7% | – |
| Financial Coaching Bench | Vals AI | 74.1% | – |
| Immigration Bench | Vals AI | 68.0% | – |
| GDP.pdf | Epoch AI Benchmarking Hub | 22.8% | – |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 42.7% | – |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 80.0% | – |
| HealthBench Professional (AA) | OpenAI | 55.8% | – |
| FACTS Parametric | 54.3%† | – | |
| Instruction following | |||
| LiveBench Language | LiveBench | 80.1% | – |
| LiveBench Instruction Following | LiveBench | 75.3% | – |
| IFBench | Artificial Analysis | – | 76.6% |
| Arena Instruction Following | Arena (LMArena) | 1435 | 1451 |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1443 | 1460 |
| EQ-Bench Creative Writing v3 | EQ-Bench | 2012† | – |
| Arena Creative Writing | Arena (LMArena) | 1421 | 1438 |
| Arena Multi-turn | Arena (LMArena) | 1435 | 1466 |
| Arena Longer Queries | Arena (LMArena) | 1454 | 1473 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1230 | – |
| LiveBench Design | LiveBench | 75.0% | – |
| MMMU-Pro | Artificial Analysis | 78.2%† | – |
| SAGE | Vals AI | 88.7% | – |
| GeoBench | GeoBench | 61.0%† | – |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 32.5%† | – |
| Furniture Assembly | Epoch AI Benchmarking Hub | 20.8% | – |
| VIALS-AA | Handshake AI | 37.9% | – |
| Code2Video-AA | Artificial Analysis | 1127 | – |
| AA-3D | Artificial Analysis | 992 | – |
| FACTS Multimodal | 40.9%† | – | |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 76.7% | 80.7% |
| MLCR | Artificial Analysis | 20.0% | – |
| FACTS Grounding | 68.6%† | – | |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 156.2† | 149.8 |
| LiveBench 2.0 | LiveBench | 67.9% | – |
| LiveBench 1.0 | LiveBench | 77.4% | – |
| AA Intelligence Index v5.0.1 | Artificial Analysis | 35.5 | – |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 46.5 | 28.4 |
| AA Progress Index v1 | Artificial Analysis | 322.7 | 297.1 |
| Vals Index | Vals AI | 58.6 | – |
| Vals Finance Index | Vals AI | 58.8% | – |
| Vals RSI Index | Vals AI | 20.2% | – |
| Vals Science Index | Vals AI | 34.8% | – |
| Vals Router Index | Vals AI | 58.6%† | – |
| Vals Legal Index | Vals AI | 72.7% | – |
| AA Cyber Index | Artificial Analysis | 56.4 | – |
| Safety & honesty | |||
| DistressBench | Scale AI SEAL | 52.4%† | – |
Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- Grok 4.7 (xhigh): BenchLeader Index 58.0 → 57.4.
- Grok 4.7 (xhigh): 8 new results (LiveBench 2.0, LiveBench Long Agentic, LiveBench 2.0 Reasoning…).
- Grok 4.7 (xhigh): 1 new result (MirrorCode).
- Qwen3.6 Max (max): BenchLeader Index 62.8 → 62.3.
- Grok 4.7 (xhigh): 1 new result (ALE-Bench).
- Grok 4.7 (xhigh): 2 score revisions.
- Grok 4.7 (xhigh): 2 score revisions.
- Grok 4.7 (xhigh): 2 score revisions.
- Grok 4.7 (xhigh): 1 score revision.
- Grok 4.7 (xhigh): BenchLeader Index 59.5 → 58.0.
Related comparisons
- Grok 4.7 vs Claude Opus 5.5
- Grok 4.7 vs GPT-6 Astra
- Grok 4.7 vs Claude Fable 5.1
- Qwen3.6 Max vs Claude Fable 5.2
- Qwen3.6 Max vs Gemini 4 Carbon
- Qwen3.6 Max vs Claude Opus 5.5
- Qwen3.6 Max vs GPT-6 Astra
- Grok 4.7 vs Claude Fable 5
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Grok 4.7 vs Qwen3.6 Max: questions
- Is Qwen3.6 Max better than Grok 4.7?
- Qwen3.6 Max (max) leads on quality: 62.1 vs 57.4. The BenchLeader Index combines every independent quality benchmark; Qwen3.6 Max (max) is ahead overall as of 16 Nov 2026, but check the category scores for your use.
- Grok 4.7 vs Qwen3.6 Max: which is cheaper, and will that change?
- Qwen3.6 Max is cheaper today: $2.92 against $3.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Grok 4.7 or Qwen3.6 Max better for coding?
- Grok 4.7 scores higher in coding (61 vs 56 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1641 for Grok 4.7 against 1482 for Qwen3.6 Max.
- Is Grok 4.7 or Qwen3.6 Max better for agents and tool use?
- Qwen3.6 Max scores higher in agentic tasks (72 vs 57 on the category index, where 50 is average).
- Which is better for long documents?
- Qwen3.6 Max scores higher on long-context benchmarks (65 vs 63). Grok 4.7 accepts more context: 500,000 against 262,144 tokens for Qwen3.6 Max.
More questions (2)
- Do independent benchmarks agree on Grok 4.7 vs Qwen3.6 Max?
- Across the 18 benchmarks both have, Grok 4.7 leads 9, Qwen3.6 Max leads 9. Every overall index that rates both puts Qwen3.6 Max ahead.
- When was Grok 4.7 released?
- Grok 4.7 was released on 21 Sep 2026.