Model comparison
GPT-6 Sol vs o4-mini
GPT-6 Sol is the stronger model overall, scoring 61.8 to 41.6 on the Noometry Index. o4-mini costs 2.1× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Last verified . 32 shared benchmarks.
Summary
- They share 32 benchmarks with published results for both. GPT-6 Sol scores higher in 8 categories and o4-mini in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 74.0 to 24.6.
- The biggest single-benchmark swing is FrontierMath Tier 4: 90% for GPT-6 Sol and 4.9% for o4-mini.
- o4-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 200K.
Side by side
| GPT-6 Sol | o4-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 61.8 | 41.6 |
| Released | 2026-09-22 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $2 | $1.10 |
| Output $ / M tokens | $10 | $4.40 |
| Results tracked | 45 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
GPT-6 Sol: 60.1 (#11), o4-mini: 40.9 (#127)
| Benchmark | GPT-6 Sol | o4-mini |
|---|---|---|
| LMArena Coding | 1447 | 1368 |
| ALE-Bench | 2,462 | 826.17 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| LMArena WebDev | 1688 | — |
| SciCode | 57.6% | — |
| GSO | — | 3.6% |
| WeirdML | — | 52.6% |
| CadEval | — | 62% |
| AlgoTune | — | 1.72 |
Agentic & Tool Use GPT-6 Sol leads
GPT-6 Sol: 37.2 (#36), o4-mini: 32.6 (#61)
| Benchmark | GPT-6 Sol | o4-mini |
|---|---|---|
| APEX-Agents | 54.3% | — |
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| GDP.pdf | 26.4% | — |
| METR Time Horizons | — | 63.9% |
| Vending-Bench 2 | 14,428 | — |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 74.0 (#9), o4-mini: 24.6 (#162)
| Benchmark | GPT-6 Sol | o4-mini |
|---|---|---|
| ARC-AGI-2 | 89.6% | 6.1% |
| ARC-AGI-1 | 95.5% | 58.7% |
| CritPt | 30.9% | 0.6% |
| LMArena Hard Prompts | 1418 | 1351 |
| Mystery Game Puzzles | 56% | 5% |
| DTBench | 97.3% | 77.6% |
| LMCA | 59.1% | 26.5% |
| Epoch Capabilities Index | 162.72 | 145.64 |
| SimpleBench | — | 38.7% |
| Kagi LLM Benchmark | — | 67.6% |
| NYT Connections (extended) | 90.1% | — |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| EBR-Bench | 53.3% | — |
| ForecastBench | — | 61.8 |
Math GPT-6 Sol leads
GPT-6 Sol: 87.2 (#7), o4-mini: 40.8 (#89)
| Benchmark | GPT-6 Sol | o4-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 89.8% | 36.1% |
| FrontierMath Tier 4 | 90% | 4.9% |
| OTIS Mock AIME 2024-2025 | 100% | 81.7% |
| LMArena Math | 1402 | 1389 |
| ProofBench | 83% | — |
| Omni-MATH | — | 72% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge GPT-6 Sol leads
GPT-6 Sol: 64.8 (#15), o4-mini: 43.6 (#91)
| Benchmark | GPT-6 Sol | o4-mini |
|---|---|---|
| GPQA Diamond | 94.3% | 79.6% |
| SimpleQA Verified | 60.7% | 19.6% |
| Vectara Hallucination Rate | 6.5% | 18.6% |
| LMArena Expert | 1439 | 1343 |
| Humanity's Last Exam | — | 18.1% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| GPQA (HELM) | — | 73.5% |
Multimodal GPT-6 Sol leads
GPT-6 Sol: 47.6 (#10), o4-mini: 40.2 (#49)
| Benchmark | GPT-6 Sol | o4-mini |
|---|---|---|
| LMArena Vision | 1245 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
| Blueprint-Bench 2 | 36.9% | — |
| Furniture Assembly | 58.3% | — |
Multilingual GPT-6 Sol leads
GPT-6 Sol: 50.5 (#118), o4-mini: 47.0 (#154)
| Benchmark | GPT-6 Sol | o4-mini |
|---|---|---|
| LMArena Non-English | 1385 | 1337 |
| LMArena Chinese | 1405 | 1354 |
| LMArena French | 1410 | 1364 |
| LMArena German | 1390 | 1336 |
| LMArena Japanese | 1385 | 1308 |
| LMArena Korean | 1341 | 1312 |
| LMArena Russian | 1401 | 1334 |
| LMArena Spanish | 1384 | 1347 |
Instruction Following Too close to call
GPT-6 Sol: 74.5 (#94), o4-mini: 75.2 (#68)
| Benchmark | GPT-6 Sol | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1412 | 1321 |
| IFEval | — | 92.8% |
Long Context o4-mini leads
GPT-6 Sol: 43.1 (#108), o4-mini: 45.5 (#33)
| Benchmark | GPT-6 Sol | o4-mini |
|---|---|---|
| LMArena Longer Query | 1411 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 71.9 (#18), o4-mini: 54.0 (#152)
| Benchmark | GPT-6 Sol | o4-mini |
|---|---|---|
| LMArena Text | 1395 | 1353 |
| LMArena Creative Writing | 1378 | 1294 |
| LMArena Multi-Turn | 1412 | 1350 |
| Short-Story Creative Writing | — | 75% |
| EQ-Bench Creative Writing | 2125 | — |
| WildBench | — | 85.4% |
Frequently asked questions
Is GPT-6 Sol better than o4-mini?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 41.6 on the Noometry Index. o4-mini costs 2.1× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Which is cheaper, GPT-6 Sol or o4-mini?
o4-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is GPT-6 Sol or o4-mini better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 40.9 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 200K.
How many benchmarks do GPT-6 Sol and o4-mini share?
32 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and o4-mini has 60.