Model comparison
GPT-5.4 Pro vs Grok-3 mini
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 41.2 on the Noometry Index.
Last verified . 6 shared benchmarks.
Summary
- They share 6 benchmarks with published results for both. GPT-5.4 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-5.4 Pro leads 70.7 to 13.6.
- The biggest single-benchmark swing is ARC-AGI-2: 83.3% for GPT-5.4 Pro and 0.4% for Grok-3 mini.
Side by side
| GPT-5.4 Pro | Grok-3 mini | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 58.9 | 41.2 |
| Released | 2026-03-05 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $30 | — |
| Output $ / M tokens | $180 | — |
| Results tracked | 16 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 Pro leads
GPT-5.4 Pro: 43.2 (#90), Grok-3 mini: 40.8 (#131)
| Benchmark | GPT-5.4 Pro | Grok-3 mini |
|---|---|---|
| WeirdML | 57.4% | 42.6% |
| Aider Polyglot | — | 49.3% |
| LMArena Coding | — | 1379 |
Reasoning GPT-5.4 Pro leads
GPT-5.4 Pro: 70.7 (#13), Grok-3 mini: 13.6 (#334)
| Benchmark | GPT-5.4 Pro | Grok-3 mini |
|---|---|---|
| ARC-AGI-2 | 83.3% | 0.4% |
| ARC-AGI-1 | 94.5% | 16.5% |
| Epoch Capabilities Index | 158.93 | 140.35 |
| SimpleBench | 74.1% | — |
| Kagi LLM Benchmark | — | 61.3% |
| CritPt | 30% | — |
| Chess Puzzles | 58.6% | — |
| EnigmaEval | 23.8% | — |
| LMArena Hard Prompts | — | 1375 |
Math GPT-5.4 Pro leads
GPT-5.4 Pro: 72.4 (#22), Grok-3 mini: 42.1 (#85)
| Benchmark | GPT-5.4 Pro | Grok-3 mini |
|---|---|---|
| FrontierMath (Feb 2025 set) | 50% | 5.9% |
| FrontierMath (Tiers 1-3) | 82.5% | — |
| FrontierMath Tier 4 | 58.5% | — |
| OTIS Mock AIME 2024-2025 | — | 77.8% |
| Omni-MATH | — | 31.8% |
| LMArena Math | — | 1386 |
| MATH Level 5 | — | 90.9% |
| FrontierMath Tier 4 (v1) | 37.5% | — |
Knowledge GPT-5.4 Pro leads
GPT-5.4 Pro: 68.3 (#7), Grok-3 mini: 46.4 (#81)
| Benchmark | GPT-5.4 Pro | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 94.6% | 76.3% |
| Humanity's Last Exam | 44.3% | — |
| SimpleQA Verified | 46.3% | — |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| Vectara Hallucination Rate | 8.3% | — |
| GPQA (HELM) | — | 67.5% |
| LMArena Expert | — | 1395 |
Multilingual Not comparable
GPT-5.4 Pro: —, Grok-3 mini: 48.1 (#145)
| Benchmark | GPT-5.4 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-5.4 Pro: —, Grok-3 mini: 78.5 (#9)
| Benchmark | GPT-5.4 Pro | Grok-3 mini |
|---|---|---|
| IFEval | — | 95.1% |
| LMArena Instruction Following | — | 1357 |
Long Context Not comparable
GPT-5.4 Pro: —, Grok-3 mini: 41.0 (#147)
| Benchmark | GPT-5.4 Pro | Grok-3 mini |
|---|---|---|
| Fiction.LiveBench | — | 66.7% |
| LMArena Longer Query | — | 1372 |
Writing & Preference Not comparable
GPT-5.4 Pro: —, Grok-3 mini: 52.5 (#169)
| Benchmark | GPT-5.4 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-5.4 Pro better than Grok-3 mini?
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 41.2 on the Noometry Index.
Is GPT-5.4 Pro or Grok-3 mini better for coding?
GPT-5.4 Pro scores higher on coding benchmarks: 43.2 versus 40.8 in the Noometry coding category.
How many benchmarks do GPT-5.4 Pro and Grok-3 mini share?
6 benchmarks have published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and Grok-3 mini has 35.