Model comparison
GPT-5.1 vs Grok 4.6
Grok 4.6 is the stronger model overall, scoring 56.9 to 49.0 on the Noometry Index.
Last verified . 36 shared benchmarks.
Summary
- They share 36 benchmarks with published results for both. GPT-5.1 scores higher in 5 categories and Grok 4.6 in 5 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.6 leads 61.4 to 39.8.
- The biggest single-benchmark swing is ARC-AGI-2: 17.6% for GPT-5.1 and 67.1% for Grok 4.6.
- Grok 4.6 is cheaper at $2 / $6 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- Grok 4.6 accepts more context: 500K tokens versus 400K.
Side by side
| GPT-5.1 | Grok 4.6 | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 49.0 | 56.9 |
| Released | 2025-11-13 | 2026-08-12 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 500K |
| Max output | 128K | 500K |
| Input $ / M tokens | $1.25 | $2 |
| Output $ / M tokens | $10 | $6 |
| Results tracked | 63 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
GPT-5.1: 46.4 (#66), Grok 4.6: 58.5 (#16)
| Benchmark | GPT-5.1 | Grok 4.6 |
|---|---|---|
| LMArena WebDev | 1395 | 1617 |
| SciCode | 43.3% | 56.5% |
| WeirdML | 60.8% | 67.3% |
| LMArena Coding | 1454 | 1465 |
| ALE-Bench | 1,192 | 1,508 |
| SWE-bench Verified | 68% | — |
| DeepSWE | — | 67.5% |
| FrontierCode | — | 48% |
| SWE-bench Verified (bash only) | 66% | — |
| CursorBench | — | 41.4% |
| FrontierSWE | — | 25.3% |
| GSO | 13.7% | — |
| LiveBench Coding | 72.5% | — |
Agentic & Tool Use Grok 4.6 leads
GPT-5.1: 32.7 (#60), Grok 4.6: 39.4 (#27)
| Benchmark | GPT-5.1 | Grok 4.6 |
|---|---|---|
| Vending-Bench 2 | 1,473 | 9,047 |
| Terminal-Bench | 47.6% | — |
| APEX-Agents | — | 65.3% |
| DeepResearch Bench | 42.8% | — |
| GDP.pdf | — | 17.2% |
| LMArena Search | 1199 | — |
Reasoning Grok 4.6 leads
GPT-5.1: 39.8 (#58), Grok 4.6: 61.4 (#20)
| Benchmark | GPT-5.1 | Grok 4.6 |
|---|---|---|
| ARC-AGI-2 | 17.6% | 67.1% |
| SimpleBench | 53.2% | 75.9% |
| ARC-AGI-1 | 72.8% | 87.5% |
| CritPt | 4.9% | 19.7% |
| Chess Puzzles | 32% | 40% |
| LMArena Hard Prompts | 1457 | 1447 |
| Mystery Game Puzzles | 19% | 34% |
| DTBench | 90.1% | 97.3% |
| LMCA | 43.9% | 48.5% |
| Epoch Capabilities Index | 149.64 | 156.44 |
| NYT Connections (extended) | — | 80% |
| EnigmaEval | 11.2% | — |
| EBR-Bench | — | 30.5% |
| LiveBench Reasoning | 95.8% | — |
| LiveBench Data Analysis | 72.1% | — |
| ForecastBench | 58.1 | — |
| LiveBench | 78.8% | — |
Math Grok 4.6 leads
GPT-5.1: 52.2 (#51), Grok 4.6: 67.0 (#24)
| Benchmark | GPT-5.1 | Grok 4.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.6% | 99.2% |
| LMArena Math | 1447 | 1423 |
| FrontierMath (Tiers 1-3) | — | 66% |
| FrontierMath Tier 4 | — | 31.7% |
| ProofBench | — | 51% |
| Omni-MATH | 46.4% | — |
| LiveBench Math | 94.5% | — |
| FrontierMath (Feb 2025 set) | 31% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge Grok 4.6 leads
GPT-5.1: 50.6 (#71), Grok 4.6: 63.3 (#20)
| Benchmark | GPT-5.1 | Grok 4.6 |
|---|---|---|
| GPQA Diamond | 87.6% | 94% |
| SimpleQA Verified | 48% | 49.3% |
| LMArena Expert | 1470 | 1467 |
| Humanity's Last Exam | 23.7% | — |
| MMLU-Pro | 57.9% | — |
| Vectara Hallucination Rate | 10.9% | — |
| GPQA (HELM) | 44.2% | — |
Multimodal GPT-5.1 leads
GPT-5.1: 44.8 (#19), Grok 4.6: 43.6 (#23)
| Benchmark | GPT-5.1 | Grok 4.6 |
|---|---|---|
| LMArena Vision | 1250 | 1263 |
| LMArena Document | 1403 | 1452 |
| VPCT | 58.7% | — |
| Blueprint-Bench 2 | — | 33.2% |
| Furniture Assembly | — | 40% |
Multilingual Too close to call
GPT-5.1: 53.8 (#56), Grok 4.6: 53.0 (#74)
| Benchmark | GPT-5.1 | Grok 4.6 |
|---|---|---|
| LMArena Non-English | 1431 | 1420 |
| LMArena Chinese | 1495 | 1480 |
| LMArena French | 1450 | 1461 |
| LMArena German | 1438 | 1431 |
| LMArena Japanese | 1453 | 1376 |
| LMArena Korean | 1401 | 1397 |
| LMArena Russian | 1435 | 1422 |
| LMArena Spanish | 1433 | 1404 |
Instruction Following GPT-5.1 leads
GPT-5.1: 83.9 (#1), Grok 4.6: 75.4 (#63)
| Benchmark | GPT-5.1 | Grok 4.6 |
|---|---|---|
| LMArena Instruction Following | 1443 | 1431 |
| LiveBench Instruction Following | 93.3% | — |
| IFEval | 93.5% | — |
Long Context GPT-5.1 leads
GPT-5.1: 47.6 (#14), Grok 4.6: 44.5 (#66)
| Benchmark | GPT-5.1 | Grok 4.6 |
|---|---|---|
| LMArena Longer Query | 1447 | 1454 |
| CL-bench | 23.7% | — |
| CL-bench Life | 17.3% | — |
Writing & Preference GPT-5.1 leads
GPT-5.1: 64.5 (#55), Grok 4.6: 62.3 (#80)
| Benchmark | GPT-5.1 | Grok 4.6 |
|---|---|---|
| LMArena Text | 1443 | 1428 |
| LMArena Creative Writing | 1427 | 1428 |
| LMArena Multi-Turn | 1450 | 1425 |
| WildBench | 86.3% | — |
| LiveBench Language | 80.2% | — |
Frequently asked questions
Is GPT-5.1 better than Grok 4.6?
Grok 4.6 is the stronger model overall, scoring 56.9 to 49.0 on the Noometry Index.
Which is cheaper, GPT-5.1 or Grok 4.6?
Grok 4.6 is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; GPT-5.1 lists at $1.25 and $10.
Is GPT-5.1 or Grok 4.6 better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 46.4 in the Noometry coding category.
Which has the bigger context window?
Grok 4.6 does, with 500K tokens against 400K.
How many benchmarks do GPT-5.1 and Grok 4.6 share?
36 benchmarks have published results for both models. GPT-5.1 has 63 scored results on Noometry and Grok 4.6 has 49.