Model comparison
GPT-6.1 Sol vs Qwen3-4B
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 31.9 on the Noometry Index.
Last verified . 3 shared benchmarks.
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. GPT-6.1 Sol scores higher in 4 categories and Qwen3-4B in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 29.7.
- The biggest single-benchmark swing is Chess Puzzles: 61% for GPT-6.1 Sol and 4% for Qwen3-4B.
- Qwen3-4B has downloadable open weights; the other is API-only.
Side by side
| GPT-6.1 Sol | Qwen3-4B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 65.6 | 31.9 |
| Released | 2026-09-29 | 2025-04-29 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 34 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-6.1 Sol: 63.2 (#8), Qwen3-4B: —
| Benchmark | GPT-6.1 Sol | Qwen3-4B |
|---|---|---|
| DeepSWE | 75.2% | — |
| FrontierCode | 50.2% | — |
| LMArena WebDev | 1755 | — |
| SciCode | 55.8% | — |
| LMArena Coding | 1487 | — |
Agentic & Tool Use GPT-6.1 Sol leads
GPT-6.1 Sol: 39.6 (#26), Qwen3-4B: 27.6 (#100)
| Benchmark | GPT-6.1 Sol | Qwen3-4B |
|---|---|---|
| APEX-Agents | 60% | — |
| Berkeley Function Calling Leaderboard | — | 35.7% |
| GDP.pdf | 32% | — |
Reasoning GPT-6.1 Sol leads
GPT-6.1 Sol: 81.9 (#2), Qwen3-4B: 19.2 (#268)
| Benchmark | GPT-6.1 Sol | Qwen3-4B |
|---|---|---|
| Chess Puzzles | 61% | 4% |
| ARC-AGI-2 | 94.2% | — |
| NYT Connections (extended) | 95.5% | — |
| ARC-AGI-1 | 98.5% | — |
| CritPt | 31.7% | — |
| EBR-Bench | 54.3% | — |
| LMArena Hard Prompts | 1466 | — |
| Mystery Game Puzzles | 80% | — |
| Epoch Capabilities Index | 166.09 | — |
Math GPT-6.1 Sol leads
GPT-6.1 Sol: 93.7 (#1), Qwen3-4B: 29.7 (#240)
| Benchmark | GPT-6.1 Sol | Qwen3-4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 52.2% |
| FrontierMath (Tiers 1-3) | 93.7% | — |
| FrontierMath Tier 4 | 100% | — |
| MathArena Final-Answer Competitions | — | 38.5% |
| ProofBench | 99% | — |
| LMArena Math | 1464 | — |
Knowledge GPT-6.1 Sol leads
GPT-6.1 Sol: 71.8 (#4), Qwen3-4B: 33.0 (#208)
| Benchmark | GPT-6.1 Sol | Qwen3-4B |
|---|---|---|
| GPQA Diamond | 95.4% | 52.3% |
| SimpleQA Verified | 73.9% | — |
| Vectara Hallucination Rate | — | 5.7% |
| LMArena Expert | 1502 | — |
Multimodal Not comparable
GPT-6.1 Sol: 52.7 (#5), Qwen3-4B: —
| Benchmark | GPT-6.1 Sol | Qwen3-4B |
|---|---|---|
| LMArena Vision | 1288 | — |
| Furniture Assembly | 80% | — |
Multilingual Not comparable
GPT-6.1 Sol: 54.3 (#46), Qwen3-4B: —
| Benchmark | GPT-6.1 Sol | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1438 | — |
| LMArena Chinese | 1477 | — |
| LMArena Russian | 1455 | — |
Instruction Following Not comparable
GPT-6.1 Sol: 77.0 (#29), Qwen3-4B: —
| Benchmark | GPT-6.1 Sol | Qwen3-4B |
|---|---|---|
| LMArena Instruction Following | 1468 | — |
Long Context Not comparable
GPT-6.1 Sol: 44.9 (#54), Qwen3-4B: —
| Benchmark | GPT-6.1 Sol | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1465 | — |
Writing & Preference Not comparable
GPT-6.1 Sol: 63.6 (#63), Qwen3-4B: —
| Benchmark | GPT-6.1 Sol | Qwen3-4B |
|---|---|---|
| LMArena Text | 1447 | — |
| LMArena Creative Writing | 1432 | — |
| LMArena Multi-Turn | 1449 | — |
Frequently asked questions
Is GPT-6.1 Sol better than Qwen3-4B?
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 31.9 on the Noometry Index.
How many benchmarks do GPT-6.1 Sol and Qwen3-4B share?
3 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Qwen3-4B has 6.