Model comparison
GPT-5.2 Pro vs Grok-3 mini
GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 41.0 on the Noometry Index.
Last verified . 3 shared benchmarks.
Summary
- They share 3 benchmarks with published results for both. GPT-5.2 Pro scores higher in 2 categories and Grok-3 mini in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.2 Pro leads 51.8 to 13.8.
- The biggest single-benchmark swing is ARC-AGI-1: 90.5% for GPT-5.2 Pro and 16.5% for Grok-3 mini.
Side by side
| GPT-5.2 Pro | Grok-3 mini | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 52.2 | 41.0 |
| Released | 2025-12-11 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $21 | — |
| Output $ / M tokens | $168 | — |
| Results tracked | 8 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5.2 Pro: —, Grok-3 mini: 40.4 (#126)
| Benchmark | GPT-5.2 Pro | Grok-3 mini |
|---|---|---|
| Aider Polyglot | — | 49.3% |
| WeirdML | — | 42.6% |
| LMArena Coding | — | 1380 |
Reasoning GPT-5.2 Pro leads
GPT-5.2 Pro: 51.8 (#31), Grok-3 mini: 13.8 (#323)
| Benchmark | GPT-5.2 Pro | Grok-3 mini |
|---|---|---|
| ARC-AGI-2 | 54.2% | 0.4% |
| ARC-AGI-1 | 90.5% | 16.5% |
| Epoch Capabilities Index | 155.41 | 140.35 |
| SimpleBench | 57.4% | — |
| Kagi LLM Benchmark | — | 61.3% |
| NYT Connections (extended) | 79.3% | — |
| LMArena Hard Prompts | — | 1374 |
Math GPT-5.2 Pro leads
GPT-5.2 Pro: 64.8 (#23), Grok-3 mini: 40.3 (#78)
| Benchmark | GPT-5.2 Pro | Grok-3 mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | — |
| FrontierMath Tier 4 | 46% | — |
| 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) | 31.3% | — |
Knowledge Not comparable
GPT-5.2 Pro: —, Grok-3 mini: 46.3 (#75)
| Benchmark | GPT-5.2 Pro | Grok-3 mini |
|---|---|---|
| GPQA Diamond | — | 76.3% |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| GPQA (HELM) | — | 67.5% |
| LMArena Expert | — | 1395 |
Multilingual Not comparable
GPT-5.2 Pro: —, Grok-3 mini: 48.3 (#141)
| Benchmark | GPT-5.2 Pro | Grok-3 mini |
|---|---|---|
| LMArena Non-English | — | 1352 |
| LMArena Chinese | — | 1387 |
| LMArena French | — | 1357 |
| LMArena German | — | 1350 |
| LMArena Japanese | — | 1343 |
| LMArena Korean | — | 1336 |
| LMArena Russian | — | 1352 |
| LMArena Spanish | — | 1379 |
Instruction Following Not comparable
GPT-5.2 Pro: —, Grok-3 mini: 78.7 (#8)
| Benchmark | GPT-5.2 Pro | Grok-3 mini |
|---|---|---|
| IFEval | — | 95.1% |
| LMArena Instruction Following | — | 1356 |
Long Context Not comparable
GPT-5.2 Pro: —, Grok-3 mini: 41.0 (#142)
| Benchmark | GPT-5.2 Pro | Grok-3 mini |
|---|---|---|
| Fiction.LiveBench | — | 66.7% |
| LMArena Longer Query | — | 1372 |
Writing & Preference Not comparable
GPT-5.2 Pro: —, Grok-3 mini: 52.7 (#163)
| Benchmark | GPT-5.2 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-5.2 Pro better than Grok-3 mini?
GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 41.0 on the Noometry Index.
How many benchmarks do GPT-5.2 Pro and Grok-3 mini share?
3 benchmarks have published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and Grok-3 mini has 35.