Model comparison
GPT-5.1 vs Grok 4
GPT-5.1 and Grok 4 score almost the same on the Noometry Index (49.0 vs 48.1), so choose on price, context window or the category you care about most.
Last verified . 37 shared benchmarks.
Summary
- They share 37 benchmarks with published results for both. GPT-5.1 scores higher in 7 categories and Grok 4 in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where Grok 4 leads 63.1 to 47.6.
- The biggest single-benchmark swing is GPQA (HELM): 44.2% for GPT-5.1 and 72.7% for Grok 4.
Side by side
| GPT-5.1 | Grok 4 | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 49.0 | 48.1 |
| Released | 2025-11-13 | 2025-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 63 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4 leads
GPT-5.1: 46.4 (#66), Grok 4: 50.3 (#46)
| Benchmark | GPT-5.1 | Grok 4 |
|---|---|---|
| WeirdML | 60.8% | 45.7% |
| LMArena Coding | 1454 | 1408 |
| SWE-bench Verified | 68% | — |
| SWE-bench Verified (bash only) | 66% | — |
| Aider Polyglot | — | 79.6% |
| LMArena WebDev | 1395 | — |
| SciCode | 43.3% | — |
| GSO | 13.7% | — |
| LiveBench Coding | 72.5% | — |
| ALE-Bench | 1,192 | — |
Agentic & Tool Use Too close to call
GPT-5.1: 32.7 (#60), Grok 4: 32.3 (#68)
| Benchmark | GPT-5.1 | Grok 4 |
|---|---|---|
| Terminal-Bench | 47.6% | 27.2% |
| DeepResearch Bench | 42.8% | 47.3% |
| LMArena Search | 1199 | 1142 |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| Cybench | — | 43% |
| BALROG | — | 43.6% |
| METR Time Horizons | — | 66.6% |
| Vending-Bench 2 | 1,473 | — |
Reasoning GPT-5.1 leads
GPT-5.1: 39.8 (#58), Grok 4: 36.7 (#65)
| Benchmark | GPT-5.1 | Grok 4 |
|---|---|---|
| ARC-AGI-2 | 17.6% | 16% |
| SimpleBench | 53.2% | 60.5% |
| ARC-AGI-1 | 72.8% | 66.7% |
| Chess Puzzles | 32% | 28% |
| LMArena Hard Prompts | 1457 | 1409 |
| Epoch Capabilities Index | 149.64 | 146.44 |
| ForecastBench | 58.1 | 60.9 |
| Kagi LLM Benchmark | — | 73.6% |
| CritPt | 4.9% | — |
| EnigmaEval | 11.2% | — |
| LiveBench Reasoning | 95.8% | — |
| Mystery Game Puzzles | 19% | — |
| DTBench | 90.1% | — |
| LiveBench Data Analysis | 72.1% | — |
| LMCA | 43.9% | — |
| LiveBench | 78.8% | — |
Math GPT-5.1 leads
GPT-5.1: 52.2 (#51), Grok 4: 48.4 (#64)
| Benchmark | GPT-5.1 | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.6% | 84% |
| Omni-MATH | 46.4% | 60.3% |
| LMArena Math | 1447 | 1422 |
| FrontierMath (Feb 2025 set) | 31% | 19.7% |
| FrontierMath Tier 4 (v1) | 12.5% | 2.1% |
| LiveBench Math | 94.5% | — |
Knowledge Grok 4 leads
GPT-5.1: 50.6 (#71), Grok 4: 53.8 (#55)
| Benchmark | GPT-5.1 | Grok 4 |
|---|---|---|
| GPQA Diamond | 87.6% | 87% |
| MMLU-Pro | 57.9% | 85.1% |
| GPQA (HELM) | 44.2% | 72.7% |
| LMArena Expert | 1470 | 1415 |
| Humanity's Last Exam | 23.7% | — |
| SimpleQA Verified | 48% | — |
| Confabulations | — | 12.4% |
| Vectara Hallucination Rate | 10.9% | — |
Multimodal GPT-5.1 leads
GPT-5.1: 44.8 (#19), Grok 4: 33.7 (#94)
| Benchmark | GPT-5.1 | Grok 4 |
|---|---|---|
| LMArena Vision | 1250 | 1210 |
| GeoBench | — | 45% |
| VPCT | 58.7% | — |
| LMArena Document | 1403 | — |
Multilingual GPT-5.1 leads
GPT-5.1: 53.8 (#56), Grok 4: 51.8 (#103)
| Benchmark | GPT-5.1 | Grok 4 |
|---|---|---|
| LMArena Non-English | 1431 | 1403 |
| LMArena Chinese | 1495 | 1427 |
| LMArena French | 1450 | 1418 |
| LMArena German | 1438 | 1429 |
| LMArena Japanese | 1453 | 1394 |
| LMArena Korean | 1401 | 1377 |
| LMArena Russian | 1435 | 1410 |
| LMArena Spanish | 1433 | 1420 |
Instruction Following GPT-5.1 leads
GPT-5.1: 83.9 (#1), Grok 4: 79.2 (#5)
| Benchmark | GPT-5.1 | Grok 4 |
|---|---|---|
| IFEval | 93.5% | 94.9% |
| LMArena Instruction Following | 1443 | 1387 |
| LiveBench Instruction Following | 93.3% | — |
Long Context Grok 4 leads
GPT-5.1: 47.6 (#14), Grok 4: 63.1 (#4)
| Benchmark | GPT-5.1 | Grok 4 |
|---|---|---|
| LMArena Longer Query | 1447 | 1409 |
| Fiction.LiveBench | — | 94.4% |
| CL-bench | 23.7% | — |
| CL-bench Life | 17.3% | — |
Writing & Preference GPT-5.1 leads
GPT-5.1: 64.5 (#55), Grok 4: 58.5 (#116)
| Benchmark | GPT-5.1 | Grok 4 |
|---|---|---|
| LMArena Text | 1443 | 1411 |
| LMArena Creative Writing | 1427 | 1397 |
| WildBench | 86.3% | 79.7% |
| LMArena Multi-Turn | 1450 | 1416 |
| Short-Story Creative Writing | — | 76.9% |
| LiveBench Language | 80.2% | — |
Frequently asked questions
Is GPT-5.1 better than Grok 4?
GPT-5.1 and Grok 4 score almost the same on the Noometry Index (49.0 vs 48.1), so choose on price, context window or the category you care about most.
Is GPT-5.1 or Grok 4 better for coding?
Grok 4 scores higher on coding benchmarks: 50.3 versus 46.4 in the Noometry coding category.
How many benchmarks do GPT-5.1 and Grok 4 share?
37 benchmarks have published results for both models. GPT-5.1 has 63 scored results on Noometry and Grok 4 has 48.