Model comparison
GPT-5 Pro vs Grok-3 mini
GPT-5 Pro is the stronger model overall, scoring 46.4 to 41.2 on the Noometry Index.
Last verified . 5 shared benchmarks.
Summary
- They share 5 benchmarks with published results for both. GPT-5 Pro scores higher in 4 categories and Grok-3 mini in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5 Pro leads 38.9 to 13.6.
- The biggest single-benchmark swing is ARC-AGI-1: 70.2% for GPT-5 Pro and 16.5% for Grok-3 mini.
Side by side
| GPT-5 Pro | Grok-3 mini | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 46.4 | 41.2 |
| Released | 2025-10-06 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | — |
| Max output | 272K | — |
| Input $ / M tokens | $15 | — |
| Output $ / M tokens | $120 | — |
| Results tracked | 12 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Pro leads
GPT-5 Pro: 44.0 (#80), Grok-3 mini: 40.8 (#131)
| Benchmark | GPT-5 Pro | Grok-3 mini |
|---|---|---|
| WeirdML | 60.4% | 42.6% |
| Aider Polyglot | — | 49.3% |
| LMArena Coding | — | 1379 |
| AlgoTune | 1.31 | — |
Reasoning GPT-5 Pro leads
GPT-5 Pro: 38.9 (#62), Grok-3 mini: 13.6 (#334)
| Benchmark | GPT-5 Pro | Grok-3 mini |
|---|---|---|
| ARC-AGI-2 | 18.3% | 0.4% |
| Kagi LLM Benchmark | 76.8% | 61.3% |
| ARC-AGI-1 | 70.2% | 16.5% |
| Epoch Capabilities Index | 150.28 | 140.35 |
| SimpleBench | 61.6% | — |
| EnigmaEval | 18.8% | — |
| LMArena Hard Prompts | — | 1375 |
Math GPT-5 Pro leads
GPT-5 Pro: 48.5 (#63), Grok-3 mini: 42.1 (#85)
| Benchmark | GPT-5 Pro | Grok-3 mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 19.5% | — |
| OTIS Mock AIME 2024-2025 | — | 77.8% |
| Omni-MATH | — | 31.8% |
| LMArena Math | — | 1386 |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge GPT-5 Pro leads
GPT-5 Pro: 56.7 (#42), Grok-3 mini: 46.4 (#81)
| Benchmark | GPT-5 Pro | Grok-3 mini |
|---|---|---|
| GPQA Diamond | — | 76.3% |
| Humanity's Last Exam | 31.6% | — |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| GPQA (HELM) | — | 67.5% |
| LMArena Expert | — | 1395 |
Multilingual Not comparable
GPT-5 Pro: —, Grok-3 mini: 48.1 (#145)
| Benchmark | GPT-5 Pro | Grok-3 mini |
|---|---|---|
| LMArena Non-English | — | 1352 |
| LMArena Chinese | — | 1387 |
| LMArena French | — | 1357 |
| LMArena German | — | 1349 |
| LMArena Japanese | — | 1342 |
| LMArena Korean | — | 1335 |
| LMArena Russian | — | 1353 |
| LMArena Spanish | — | 1381 |
Instruction Following Not comparable
GPT-5 Pro: —, Grok-3 mini: 78.5 (#9)
| Benchmark | GPT-5 Pro | Grok-3 mini |
|---|---|---|
| IFEval | — | 95.1% |
| LMArena Instruction Following | — | 1357 |
Long Context Not comparable
GPT-5 Pro: —, Grok-3 mini: 41.0 (#147)
| Benchmark | GPT-5 Pro | Grok-3 mini |
|---|---|---|
| Fiction.LiveBench | — | 66.7% |
| LMArena Longer Query | — | 1372 |
Writing & Preference Not comparable
GPT-5 Pro: —, Grok-3 mini: 52.5 (#169)
| Benchmark | GPT-5 Pro | Grok-3 mini |
|---|---|---|
| LMArena Text | — | 1370 |
| LMArena Creative Writing | — | 1342 |
| Short-Story Creative Writing | — | 73.5% |
| WildBench | — | 65.1% |
| LMArena Multi-Turn | — | 1355 |
Frequently asked questions
Is GPT-5 Pro better than Grok-3 mini?
GPT-5 Pro is the stronger model overall, scoring 46.4 to 41.2 on the Noometry Index.
Is GPT-5 Pro or Grok-3 mini better for coding?
GPT-5 Pro scores higher on coding benchmarks: 44.0 versus 40.8 in the Noometry coding category.
How many benchmarks do GPT-5 Pro and Grok-3 mini share?
5 benchmarks have published results for both models. GPT-5 Pro has 12 scored results on Noometry and Grok-3 mini has 35.