Model comparison
GPT-5.1 vs Qwen3.5 397B-A17B
GPT-5.1 is the stronger model overall, scoring 49.0 to 46.0 on the Noometry Index. Qwen3.5 397B-A17B costs 2.5× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
Alibaba (Qwen)Summary
- They share 26 benchmarks with published results for both. GPT-5.1 scores higher in 8 categories and Qwen3.5 397B-A17B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where GPT-5.1 leads 83.9 to 75.0.
- The biggest single-benchmark swing is Chess Puzzles: 32% for GPT-5.1 and 13% for Qwen3.5 397B-A17B.
- Qwen3.5 397B-A17B is cheaper at $0.60 / $3.60 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- GPT-5.1 accepts more context: 400K tokens versus 262K.
- Qwen3.5 397B-A17B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.1 | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 49.0 | 46.0 |
| Released | 2025-11-13 | 2026-02-01 |
| Weights | Proprietary | Open |
| Context window | 400K | 262K |
| Max output | 128K | 66K |
| Input $ / M tokens | $1.25 | $0.60 |
| Output $ / M tokens | $10 | $3.60 |
| Results tracked | 63 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
GPT-5.1: 46.4 (#66), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | GPT-5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena WebDev | 1395 | 1400 |
| LMArena Coding | 1454 | 1465 |
| SWE-bench Verified | 68% | — |
| SWE-bench Verified (bash only) | 66% | — |
| SciCode | 43.3% | — |
| GSO | 13.7% | — |
| WeirdML | 60.8% | — |
| LiveBench Coding | 72.5% | — |
| ALE-Bench | 1,192 | — |
Agentic & Tool Use Too close to call
GPT-5.1: 32.7 (#60), Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | GPT-5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| Terminal-Bench | 47.6% | — |
| APEX-Agents | — | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
| DeepResearch Bench | 42.8% | — |
| LMArena Search | 1199 | — |
| Vending-Bench 2 | 1,473 | — |
Reasoning GPT-5.1 leads
GPT-5.1: 39.8 (#58), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | GPT-5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| Chess Puzzles | 32% | 13% |
| LMArena Hard Prompts | 1457 | 1448 |
| Mystery Game Puzzles | 19% | 18% |
| DTBench | 90.1% | 87.5% |
| LMCA | 43.9% | 37.9% |
| Epoch Capabilities Index | 149.64 | 146.65 |
| ARC-AGI-2 | 17.6% | — |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | — | 73.7% |
| NYT Connections (extended) | — | 58.9% |
| ARC-AGI-1 | 72.8% | — |
| CritPt | 4.9% | — |
| EnigmaEval | 11.2% | — |
| Thematic Generalization | — | 65.1% |
| LiveBench Reasoning | 95.8% | — |
| LiveBench Data Analysis | 72.1% | — |
| ForecastBench | 58.1 | — |
| LiveBench | 78.8% | — |
Math GPT-5.1 leads
GPT-5.1: 52.2 (#51), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | GPT-5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.6% | 88.9% |
| LMArena Math | 1447 | 1454 |
| FrontierMath (Tiers 1-3) | — | 31.2% |
| Omni-MATH | 46.4% | — |
| LiveBench Math | 94.5% | — |
| FrontierMath (Feb 2025 set) | 31% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge Qwen3.5 397B-A17B leads
GPT-5.1: 50.6 (#71), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | GPT-5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| GPQA Diamond | 87.6% | 86.4% |
| LMArena Expert | 1470 | 1462 |
| Humanity's Last Exam | 23.7% | — |
| SimpleQA Verified | 48% | — |
| MMLU-Pro | 57.9% | — |
| Vectara Hallucination Rate | 10.9% | — |
| GPQA (HELM) | 44.2% | — |
Multimodal GPT-5.1 leads
GPT-5.1: 44.8 (#19), Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | GPT-5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | 1250 | 1263 |
| VPCT | 58.7% | — |
| LMArena Document | 1403 | — |
Multilingual Too close to call
GPT-5.1: 53.8 (#56), Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | GPT-5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1431 | 1430 |
| LMArena Chinese | 1495 | 1500 |
| LMArena French | 1450 | 1461 |
| LMArena German | 1438 | 1447 |
| LMArena Japanese | 1453 | 1426 |
| LMArena Korean | 1401 | 1384 |
| LMArena Russian | 1435 | 1429 |
| LMArena Spanish | 1433 | 1441 |
Instruction Following GPT-5.1 leads
GPT-5.1: 83.9 (#1), Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | GPT-5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1443 | 1424 |
| LiveBench Instruction Following | 93.3% | — |
| IFEval | 93.5% | — |
Long Context GPT-5.1 leads
GPT-5.1: 47.6 (#14), Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | GPT-5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1447 | 1442 |
| CL-bench | 23.7% | — |
| CL-bench Life | 17.3% | — |
Writing & Preference GPT-5.1 leads
GPT-5.1: 64.5 (#55), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | GPT-5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1443 | 1438 |
| LMArena Creative Writing | 1427 | 1401 |
| LMArena Multi-Turn | 1450 | 1446 |
| EQ-Bench Creative Writing | — | 1478 |
| WildBench | 86.3% | — |
| LiveBench Language | 80.2% | — |
Frequently asked questions
Is GPT-5.1 better than Qwen3.5 397B-A17B?
GPT-5.1 is the stronger model overall, scoring 49.0 to 46.0 on the Noometry Index. Qwen3.5 397B-A17B costs 2.5× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Which is cheaper, GPT-5.1 or Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is cheaper. It lists at $0.60 per million input tokens and $3.60 per million output tokens; GPT-5.1 lists at $1.25 and $10.
Is GPT-5.1 or Qwen3.5 397B-A17B better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.4 versus 42.0 in the Noometry coding category.
Which has the bigger context window?
GPT-5.1 does, with 400K tokens against 262K.
How many benchmarks do GPT-5.1 and Qwen3.5 397B-A17B share?
26 benchmarks have published results for both models. GPT-5.1 has 63 scored results on Noometry and Qwen3.5 397B-A17B has 36.