Model comparison
GPT-6.1 Sol vs Step 5 Preview
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 47.9 on the Noometry Index. Step 5 Preview costs 2.8× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
StepFunSummary
- They share 17 benchmarks with published results for both. GPT-6.1 Sol scores higher in 9 categories and Step 5 Preview in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 46.1.
- The biggest single-benchmark swing is ProofBench: 99% for GPT-6.1 Sol and 42% for Step 5 Preview.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
- GPT-6.1 Sol accepts more context: 1.05M tokens versus 1.02M.
Side by side
| GPT-6.1 Sol | Step 5 Preview | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 65.6 | 47.9 |
| Released | 2026-09-29 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.02M |
| Max output | 128K | 66K |
| Input $ / M tokens | $2 | $1 |
| Output $ / M tokens | $10 | $2.70 |
| Results tracked | 34 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6.1 Sol leads
GPT-6.1 Sol: 63.2 (#8), Step 5 Preview: 51.8 (#36)
| Benchmark | GPT-6.1 Sol | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1755 | 1564 |
| SciCode | 55.8% | 58.9% |
| LMArena Coding | 1487 | 1480 |
| DeepSWE | 75.2% | — |
| FrontierCode | 50.2% | — |
Agentic & Tool Use Not comparable
GPT-6.1 Sol: 39.6 (#26), Step 5 Preview: —
| Benchmark | GPT-6.1 Sol | Step 5 Preview |
|---|---|---|
| APEX-Agents | 60% | — |
| GDP.pdf | 32% | — |
Reasoning GPT-6.1 Sol leads
GPT-6.1 Sol: 81.9 (#2), Step 5 Preview: 40.0 (#57)
| Benchmark | GPT-6.1 Sol | Step 5 Preview |
|---|---|---|
| CritPt | 31.7% | 20.9% |
| LMArena Hard Prompts | 1466 | 1465 |
| ARC-AGI-2 | 94.2% | — |
| NYT Connections (extended) | 95.5% | — |
| ARC-AGI-1 | 98.5% | — |
| Chess Puzzles | 61% | — |
| EBR-Bench | 54.3% | — |
| Mystery Game Puzzles | 80% | — |
| Epoch Capabilities Index | 166.09 | — |
Math GPT-6.1 Sol leads
GPT-6.1 Sol: 93.7 (#1), Step 5 Preview: 46.1 (#72)
| Benchmark | GPT-6.1 Sol | Step 5 Preview |
|---|---|---|
| ProofBench | 99% | 42% |
| LMArena Math | 1464 | 1470 |
| FrontierMath (Tiers 1-3) | 93.7% | — |
| FrontierMath Tier 4 | 100% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
Knowledge GPT-6.1 Sol leads
GPT-6.1 Sol: 71.8 (#4), Step 5 Preview: 41.2 (#112)
| Benchmark | GPT-6.1 Sol | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1502 | 1470 |
| GPQA Diamond | 95.4% | — |
| SimpleQA Verified | 73.9% | — |
Multimodal GPT-6.1 Sol leads
GPT-6.1 Sol: 52.7 (#5), Step 5 Preview: 41.0 (#41)
| Benchmark | GPT-6.1 Sol | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1288 | 1267 |
| Furniture Assembly | 80% | — |
Multilingual Too close to call
GPT-6.1 Sol: 54.3 (#46), Step 5 Preview: 53.8 (#54)
| Benchmark | GPT-6.1 Sol | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1438 | 1432 |
| LMArena Chinese | 1477 | 1519 |
| LMArena Russian | 1455 | 1436 |
| LMArena Spanish | — | 1439 |
Instruction Following GPT-6.1 Sol leads
GPT-6.1 Sol: 77.0 (#29), Step 5 Preview: 76.0 (#50)
| Benchmark | GPT-6.1 Sol | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1468 | 1444 |
Long Context Too close to call
GPT-6.1 Sol: 44.9 (#54), Step 5 Preview: 44.5 (#64)
| Benchmark | GPT-6.1 Sol | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1465 | 1455 |
Writing & Preference Too close to call
GPT-6.1 Sol: 63.6 (#63), Step 5 Preview: 62.8 (#71)
| Benchmark | GPT-6.1 Sol | Step 5 Preview |
|---|---|---|
| LMArena Text | 1447 | 1442 |
| LMArena Creative Writing | 1432 | 1410 |
| LMArena Multi-Turn | 1449 | 1447 |
Frequently asked questions
Is GPT-6.1 Sol better than Step 5 Preview?
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 47.9 on the Noometry Index. Step 5 Preview costs 2.8× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Which is cheaper, GPT-6.1 Sol or Step 5 Preview?
Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; GPT-6.1 Sol lists at $2 and $10.
Is GPT-6.1 Sol or Step 5 Preview better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 51.8 in the Noometry coding category.
Which has the bigger context window?
GPT-6.1 Sol does, with 1.05M tokens against 1.02M.
How many benchmarks do GPT-6.1 Sol and Step 5 Preview share?
17 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Step 5 Preview has 18.