Model comparison
GPT-6 Astra vs Grok-3 mini
GPT-6 Astra is the stronger model overall, scoring 70.8 to 41.2 on the Noometry Index.
Last verified . 23 shared benchmarks.
Summary
- They share 23 benchmarks with published results for both. GPT-6 Astra scores higher in 7 categories and Grok-3 mini in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Astra leads 85.1 to 13.6.
- The biggest single-benchmark swing is ARC-AGI-2: 95% for GPT-6 Astra and 0.4% for Grok-3 mini.
Side by side
| GPT-6 Astra | Grok-3 mini | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 70.8 | 41.2 |
| Released | 2026-09-03 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $10 | — |
| Output $ / M tokens | $50 | — |
| Results tracked | 56 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Astra leads
GPT-6 Astra: 73.7 (#2), Grok-3 mini: 40.8 (#131)
| Benchmark | GPT-6 Astra | Grok-3 mini |
|---|---|---|
| WeirdML | 93.6% | 42.6% |
| LMArena Coding | 1487 | 1379 |
| DeepSWE | 74.1% | — |
| FrontierCode | 53.3% | — |
| Aider Polyglot | — | 49.3% |
| LMArena WebDev | 1786 | — |
| FrontierSWE | 65.5% | — |
| SciCode | 56.5% | — |
| GSO | 79.4% | — |
| MirrorCode | 46.7% | — |
| ALE-Bench | 2,951 | — |
Agentic & Tool Use Not comparable
GPT-6 Astra: 52.9 (#3), Grok-3 mini: —
| Benchmark | GPT-6 Astra | Grok-3 mini |
|---|---|---|
| APEX-Agents | 64.7% | — |
| Remote Labor Index | 20.8% | — |
| BALROG | 68.3% | — |
| GDP.pdf | 34.2% | — |
| Vending-Bench 2 | 15,515 | — |
Reasoning GPT-6 Astra leads
GPT-6 Astra: 85.1 (#1), Grok-3 mini: 13.6 (#334)
| Benchmark | GPT-6 Astra | Grok-3 mini |
|---|---|---|
| ARC-AGI-2 | 95% | 0.4% |
| ARC-AGI-1 | 98.5% | 16.5% |
| LMArena Hard Prompts | 1462 | 1375 |
| Epoch Capabilities Index | 166.45 | 140.35 |
| Kagi LLM Benchmark | — | 61.3% |
| NYT Connections (extended) | 98.1% | — |
| CritPt | 31.7% | — |
| Chess Puzzles | 72% | — |
| EBR-Bench | 76.2% | — |
| Mystery Game Puzzles | 84% | — |
| DTBench | 97.3% | — |
| LMCA | 64.4% | — |
| Bench to the Future 3 | 0.14 | — |
Math GPT-6 Astra leads
GPT-6 Astra: 93.5 (#2), Grok-3 mini: 42.1 (#85)
| Benchmark | GPT-6 Astra | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 77.8% |
| LMArena Math | 1465 | 1386 |
| FrontierMath (Tiers 1-3) | 93.7% | — |
| FrontierMath Tier 4 | 97.6% | — |
| ProofBench | 99% | — |
| Omni-MATH | — | 31.8% |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
| FrontierMath Erdős | 2.9% | — |
Knowledge GPT-6 Astra leads
GPT-6 Astra: 75.3 (#1), Grok-3 mini: 46.4 (#81)
| Benchmark | GPT-6 Astra | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 95.8% | 76.3% |
| LMArena Expert | 1483 | 1395 |
| Humanity's Last Exam | 54.8% | — |
| SimpleQA Verified | 75.6% | — |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| Vectara Hallucination Rate | 8.7% | — |
| GPQA (HELM) | — | 67.5% |
Multimodal Not comparable
GPT-6 Astra: 55.0 (#3), Grok-3 mini: —
| Benchmark | GPT-6 Astra | Grok-3 mini |
|---|---|---|
| LMArena Vision | 1281 | — |
| Blueprint-Bench 2 | 49.7% | — |
| Furniture Assembly | 80% | — |
| LMArena Document | 1468 | — |
Multilingual GPT-6 Astra leads
GPT-6 Astra: 53.7 (#61), Grok-3 mini: 48.1 (#145)
| Benchmark | GPT-6 Astra | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1430 | 1352 |
| LMArena Chinese | 1484 | 1387 |
| LMArena French | 1456 | 1357 |
| LMArena German | 1440 | 1349 |
| LMArena Japanese | 1379 | 1342 |
| LMArena Korean | 1426 | 1335 |
| LMArena Russian | 1436 | 1353 |
| LMArena Spanish | 1407 | 1381 |
Instruction Following Grok-3 mini leads
GPT-6 Astra: 76.3 (#44), Grok-3 mini: 78.5 (#9)
| Benchmark | GPT-6 Astra | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1450 | 1357 |
| IFEval | — | 95.1% |
Long Context GPT-6 Astra leads
GPT-6 Astra: 44.5 (#62), Grok-3 mini: 41.0 (#147)
| Benchmark | GPT-6 Astra | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1456 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference GPT-6 Astra leads
GPT-6 Astra: 75.3 (#7), Grok-3 mini: 52.5 (#169)
| Benchmark | GPT-6 Astra | Grok-3 mini |
|---|---|---|
| LMArena Text | 1441 | 1370 |
| LMArena Creative Writing | 1418 | 1342 |
| LMArena Multi-Turn | 1448 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| EQ-Bench Creative Writing | 2173 | — |
| WildBench | — | 65.1% |
Frequently asked questions
Is GPT-6 Astra better than Grok-3 mini?
GPT-6 Astra is the stronger model overall, scoring 70.8 to 41.2 on the Noometry Index.
Is GPT-6 Astra or Grok-3 mini better for coding?
GPT-6 Astra scores higher on coding benchmarks: 73.7 versus 40.8 in the Noometry coding category.
How many benchmarks do GPT-6 Astra and Grok-3 mini share?
23 benchmarks have published results for both models. GPT-6 Astra has 56 scored results on Noometry and Grok-3 mini has 35.