Model comparison
GPT-6.1 Sol vs Qwen3 32B
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 39.2 on the Noometry Index. Qwen3 32B costs 3.3× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. GPT-6.1 Sol scores higher in 9 categories and Qwen3 32B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6.1 Sol leads 81.9 to 20.2.
- The biggest single-benchmark swing is Chess Puzzles: 61% for GPT-6.1 Sol and 5% for Qwen3 32B.
- Qwen3 32B is cheaper at $0.70 / $2.80 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
- GPT-6.1 Sol accepts more context: 1.05M tokens versus 131K.
- Qwen3 32B has downloadable open weights; the other is API-only.
Side by side
| GPT-6.1 Sol | Qwen3 32B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 65.6 | 39.2 |
| Released | 2026-09-29 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 128K | 16K |
| Input $ / M tokens | $2 | $0.70 |
| Output $ / M tokens | $10 | $2.80 |
| Results tracked | 34 | 26 |
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), Qwen3 32B: 37.7 (#190)
| Benchmark | GPT-6.1 Sol | Qwen3 32B |
|---|---|---|
| SciCode | 55.8% | 35.4% |
| LMArena Coding | 1487 | 1358 |
| DeepSWE | 75.2% | — |
| FrontierCode | 50.2% | — |
| Aider Polyglot | — | 40% |
| LMArena WebDev | 1755 | — |
Agentic & Tool Use GPT-6.1 Sol leads
GPT-6.1 Sol: 39.6 (#26), Qwen3 32B: 32.6 (#62)
| Benchmark | GPT-6.1 Sol | Qwen3 32B |
|---|---|---|
| APEX-Agents | 60% | — |
| Berkeley Function Calling Leaderboard | — | 48.7% |
| GDP.pdf | 32% | — |
Reasoning GPT-6.1 Sol leads
GPT-6.1 Sol: 81.9 (#2), Qwen3 32B: 20.2 (#241)
| Benchmark | GPT-6.1 Sol | Qwen3 32B |
|---|---|---|
| CritPt | 31.7% | 0.3% |
| Chess Puzzles | 61% | 5% |
| LMArena Hard Prompts | 1466 | 1334 |
| Epoch Capabilities Index | 166.09 | 138.51 |
| ARC-AGI-2 | 94.2% | — |
| Kagi LLM Benchmark | — | 54.9% |
| NYT Connections (extended) | 95.5% | — |
| ARC-AGI-1 | 98.5% | — |
| EBR-Bench | 54.3% | — |
| Mystery Game Puzzles | 80% | — |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
Math GPT-6.1 Sol leads
GPT-6.1 Sol: 93.7 (#1), Qwen3 32B: 39.7 (#99)
| Benchmark | GPT-6.1 Sol | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 66.9% |
| LMArena Math | 1464 | 1399 |
| FrontierMath (Tiers 1-3) | 93.7% | — |
| FrontierMath Tier 4 | 100% | — |
| ProofBench | 99% | — |
Knowledge GPT-6.1 Sol leads
GPT-6.1 Sol: 71.8 (#4), Qwen3 32B: 40.0 (#125)
| Benchmark | GPT-6.1 Sol | Qwen3 32B |
|---|---|---|
| GPQA Diamond | 95.4% | 65.7% |
| LMArena Expert | 1502 | 1362 |
| SimpleQA Verified | 73.9% | — |
| Vectara Hallucination Rate | — | 5.9% |
Multimodal Not comparable
GPT-6.1 Sol: 52.7 (#5), Qwen3 32B: —
| Benchmark | GPT-6.1 Sol | Qwen3 32B |
|---|---|---|
| LMArena Vision | 1288 | — |
| Furniture Assembly | 80% | — |
Multilingual GPT-6.1 Sol leads
GPT-6.1 Sol: 54.3 (#46), Qwen3 32B: 45.6 (#167)
| Benchmark | GPT-6.1 Sol | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1438 | 1317 |
| LMArena Chinese | 1477 | 1357 |
| LMArena Russian | 1455 | 1311 |
| LMArena German | — | 1341 |
Instruction Following GPT-6.1 Sol leads
GPT-6.1 Sol: 77.0 (#29), Qwen3 32B: 68.9 (#179)
| Benchmark | GPT-6.1 Sol | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1468 | 1305 |
Long Context GPT-6.1 Sol leads
GPT-6.1 Sol: 44.9 (#54), Qwen3 32B: 43.8 (#87)
| Benchmark | GPT-6.1 Sol | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1465 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference GPT-6.1 Sol leads
GPT-6.1 Sol: 63.6 (#63), Qwen3 32B: 52.9 (#163)
| Benchmark | GPT-6.1 Sol | Qwen3 32B |
|---|---|---|
| LMArena Text | 1447 | 1340 |
| LMArena Creative Writing | 1432 | 1297 |
| LMArena Multi-Turn | 1449 | 1331 |
Frequently asked questions
Is GPT-6.1 Sol better than Qwen3 32B?
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 39.2 on the Noometry Index. Qwen3 32B costs 3.3× 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 Qwen3 32B?
Qwen3 32B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; GPT-6.1 Sol lists at $2 and $10.
Is GPT-6.1 Sol or Qwen3 32B better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 37.7 in the Noometry coding category.
Which has the bigger context window?
GPT-6.1 Sol does, with 1.05M tokens against 131K.
How many benchmarks do GPT-6.1 Sol and Qwen3 32B share?
18 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Qwen3 32B has 26.