Model comparison
GPT-6 Astra vs o1-mini
GPT-6 Astra is the stronger model overall, scoring 70.3 to 33.7 on the Noometry Index.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. GPT-6 Astra scores higher in 9 categories and o1-mini in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Astra leads 85.1 to 8.9.
- The biggest single-benchmark swing is ARC-AGI-2: 95% for GPT-6 Astra and 0.8% for o1-mini.
Side by side
| GPT-6 Astra | o1-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 70.3 | 33.7 |
| Released | 2026-09-03 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $10 | — |
| Output $ / M tokens | $50 | — |
| Results tracked | 51 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Astra leads
GPT-6 Astra: 70.5 (#3), o1-mini: 35.1 (#218)
| Benchmark | GPT-6 Astra | o1-mini |
|---|---|---|
| WeirdML | 93.6% | 36.3% |
| LMArena Coding | 1488 | 1362 |
| DeepSWE | 74.1% | — |
| FrontierCode | 53.3% | — |
| Aider Polyglot | — | 32.9% |
| LMArena WebDev | 1792 | — |
| FrontierSWE | 65.5% | — |
| SciCode | 56.5% | — |
| LiveBench Coding | — | 48% |
| MirrorCode | 46.7% | — |
| ALE-Bench | 2,951 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use GPT-6 Astra leads
GPT-6 Astra: 52.3 (#3), o1-mini: 24.3 (#112)
| Benchmark | GPT-6 Astra | o1-mini |
|---|---|---|
| APEX-Agents | 64.7% | — |
| Remote Labor Index | 20.8% | — |
| Cybench | — | 10% |
| BALROG | 68.3% | — |
| Vending-Bench 2 | 15,515 | — |
Reasoning GPT-6 Astra leads
GPT-6 Astra: 85.1 (#1), o1-mini: 8.9 (#340)
| Benchmark | GPT-6 Astra | o1-mini |
|---|---|---|
| ARC-AGI-2 | 95% | 0.8% |
| ARC-AGI-1 | 98.5% | 14% |
| LMArena Hard Prompts | 1464 | 1333 |
| Epoch Capabilities Index | 166.6 | 135.82 |
| SimpleBench | — | 18.1% |
| NYT Connections (extended) | 98.1% | — |
| CritPt | 31.7% | — |
| Chess Puzzles | 72% | — |
| EBR-Bench | 76.2% | — |
| LiveBench Reasoning | — | 72.3% |
| Mystery Game Puzzles | 84% | — |
| DTBench | 97.3% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 64.4% | — |
| Bench to the Future 3 | 0.14 | — |
| LiveBench | — | 57.8% |
Math GPT-6 Astra leads
GPT-6 Astra: 93.4 (#1), o1-mini: 33.7 (#168)
| Benchmark | GPT-6 Astra | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 46.9% |
| LMArena Math | 1463 | 1358 |
| FrontierMath (Tiers 1-3) | 93.7% | — |
| FrontierMath Tier 4 | 97.6% | — |
| ProofBench | 99% | — |
| LiveBench Math | — | 62% |
| MATH Level 5 | — | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
| FrontierMath Erdős | 2.9% | — |
Knowledge GPT-6 Astra leads
GPT-6 Astra: 75.3 (#1), o1-mini: 34.8 (#180)
| Benchmark | GPT-6 Astra | o1-mini |
|---|---|---|
| GPQA Diamond | 95.8% | 62.4% |
| LMArena Expert | 1486 | 1316 |
| Humanity's Last Exam | 54.8% | — |
| SimpleQA Verified | 75.6% | — |
| Confabulations | — | 18.6% |
| Vectara Hallucination Rate | 8.7% | — |
Multimodal Not comparable
GPT-6 Astra: 55.1 (#3), o1-mini: —
| Benchmark | GPT-6 Astra | o1-mini |
|---|---|---|
| LMArena Vision | 1280 | — |
| Blueprint-Bench 2 | 49.7% | — |
| Furniture Assembly | 80% | — |
| LMArena Document | 1468 | — |
Multilingual GPT-6 Astra leads
GPT-6 Astra: 54.0 (#53), o1-mini: 43.8 (#177)
| Benchmark | GPT-6 Astra | o1-mini |
|---|---|---|
| LMArena Non-English | 1431 | 1289 |
| LMArena Chinese | 1495 | 1314 |
| LMArena French | 1467 | 1292 |
| LMArena Russian | 1434 | 1283 |
| LMArena Spanish | 1412 | 1302 |
| LMArena German | — | 1278 |
| LMArena Japanese | — | 1245 |
| LMArena Korean | — | 1223 |
Instruction Following GPT-6 Astra leads
GPT-6 Astra: 76.6 (#37), o1-mini: 67.0 (#200)
| Benchmark | GPT-6 Astra | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1454 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
Long Context GPT-6 Astra leads
GPT-6 Astra: 44.7 (#57), o1-mini: 40.1 (#156)
| Benchmark | GPT-6 Astra | o1-mini |
|---|---|---|
| LMArena Longer Query | 1460 | 1321 |
Writing & Preference GPT-6 Astra leads
GPT-6 Astra: 75.7 (#7), o1-mini: 48.6 (#196)
| Benchmark | GPT-6 Astra | o1-mini |
|---|---|---|
| LMArena Text | 1443 | 1317 |
| LMArena Creative Writing | 1423 | 1244 |
| LMArena Multi-Turn | 1457 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| EQ-Bench Creative Writing | 2173 | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is GPT-6 Astra better than o1-mini?
GPT-6 Astra is the stronger model overall, scoring 70.3 to 33.7 on the Noometry Index.
Is GPT-6 Astra or o1-mini better for coding?
GPT-6 Astra scores higher on coding benchmarks: 70.5 versus 35.1 in the Noometry coding category.
How many benchmarks do GPT-6 Astra and o1-mini share?
20 benchmarks have published results for both models. GPT-6 Astra has 51 scored results on Noometry and o1-mini has 39.