Model comparison
o3 vs Qwen3.7 Plus
o3 is the stronger model overall, scoring 47.5 to 45.3 on the Noometry Index. Qwen3.7 Plus costs 5.0× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Alibaba (Qwen)Summary
- They share 27 benchmarks with published results for both. o3 scores higher in 3 categories and Qwen3.7 Plus in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where o3 leads 34.5 to 21.4.
- The biggest single-benchmark swing is Chess Puzzles: 38% for o3 and 24% for Qwen3.7 Plus.
- Qwen3.7 Plus is cheaper at $0.40 / $1.60 per million input/output tokens, against $2 / $8 for o3.
- Qwen3.7 Plus accepts more context: 1M tokens versus 200K.
Side by side
| o3 | Qwen3.7 Plus | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 47.5 | 45.3 |
| Released | 2025-04-16 | 2026-06-02 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1M |
| Max output | 100K | 131K |
| Input $ / M tokens | $2 | $0.40 |
| Output $ / M tokens | $8 | $1.60 |
| Results tracked | 63 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
o3: 46.8 (#64), Qwen3.7 Plus: 36.6 (#206)
| Benchmark | o3 | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1408 | 1473 |
| SWE-bench Verified | 62.3% | — |
| FrontierCode | — | 10.2% |
| SWE-bench Verified (bash only) | 58.4% | — |
| Aider Polyglot | 81.3% | — |
| SciCode | — | 45.5% |
| GSO | 8.8% | — |
| WeirdML | 52.4% | — |
| CadEval | 74% | — |
| ALE-Bench | 933.55 | — |
Agentic & Tool Use o3 leads
o3: 34.5 (#44), Qwen3.7 Plus: 21.4 (#138)
| Benchmark | o3 | Qwen3.7 Plus |
|---|---|---|
| Berkeley Function Calling Leaderboard | 63% | — |
| OSWorld 2.0 | — | 2.8% |
| GDPval | 30.8% | — |
| DeepResearch Bench | 45.2% | — |
| OSWorld | 23% | — |
| LMArena Search | 1144 | — |
| METR Time Horizons | 65.4% | — |
Reasoning Qwen3.7 Plus leads
o3: 32.0 (#78), Qwen3.7 Plus: 39.3 (#59)
| Benchmark | o3 | Qwen3.7 Plus |
|---|---|---|
| CritPt | 1.4% | 9.1% |
| Chess Puzzles | 38% | 24% |
| LMArena Hard Prompts | 1402 | 1460 |
| Mystery Game Puzzles | 29% | 17% |
| DTBench | 84.8% | 84% |
| LMCA | 39.7% | 37.6% |
| Epoch Capabilities Index | 146.86 | 147.37 |
| ARC-AGI-2 | 6.5% | — |
| SimpleBench | 53.1% | — |
| Kagi LLM Benchmark | 67.6% | — |
| NYT Connections (extended) | — | 74.8% |
| ARC-AGI-1 | 60.8% | — |
| EnigmaEval | 13.1% | — |
| ForecastBench | 62.5 | — |
Math Too close to call
o3: 50.2 (#58), Qwen3.7 Plus: 50.5 (#56)
| Benchmark | o3 | Qwen3.7 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 33.3% | 34.4% |
| OTIS Mock AIME 2024-2025 | 84.4% | 93.3% |
| LMArena Math | 1426 | 1466 |
| Omni-MATH | 71.4% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 18.7% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Too close to call
o3: 54.6 (#52), Qwen3.7 Plus: 54.9 (#51)
| Benchmark | o3 | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 81.8% | 87.9% |
| LMArena Expert | 1402 | 1467 |
| Humanity's Last Exam | 20.3% | — |
| SimpleQA Verified | 49.4% | — |
| MMLU-Pro | 85.9% | — |
| Confabulations | 14.4% | — |
| GPQA (HELM) | 75.3% | — |
Multimodal Too close to call
o3: 41.4 (#36), Qwen3.7 Plus: 41.8 (#33)
| Benchmark | o3 | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | 1214 | 1279 |
| GeoBench | 74% | — |
| VPCT | 52% | — |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
o3: 51.7 (#105), Qwen3.7 Plus: 54.8 (#38)
| Benchmark | o3 | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1401 | 1445 |
| LMArena Chinese | 1437 | 1510 |
| LMArena French | 1430 | 1473 |
| LMArena German | 1420 | 1471 |
| LMArena Japanese | 1403 | 1413 |
| LMArena Korean | 1370 | 1415 |
| LMArena Russian | 1406 | 1457 |
| LMArena Spanish | 1395 | 1457 |
Instruction Following Qwen3.7 Plus leads
o3: 72.8 (#127), Qwen3.7 Plus: 75.8 (#52)
| Benchmark | o3 | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1368 | 1440 |
| IFEval | 86.9% | — |
Long Context o3 leads
o3: 53.3 (#6), Qwen3.7 Plus: 44.5 (#65)
| Benchmark | o3 | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1372 | 1455 |
| Fiction.LiveBench | 88.9% | — |
| CL-bench | 17.8% | — |
Writing & Preference Too close to call
o3: 63.5 (#64), Qwen3.7 Plus: 64.3 (#56)
| Benchmark | o3 | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1410 | 1455 |
| LMArena Creative Writing | 1359 | 1439 |
| LMArena Multi-Turn | 1405 | 1460 |
| Short-Story Creative Writing | 83.9% | — |
| EQ-Bench Creative Writing | 1676 | — |
| WildBench | 86.1% | — |
Frequently asked questions
Is o3 better than Qwen3.7 Plus?
o3 is the stronger model overall, scoring 47.5 to 45.3 on the Noometry Index. Qwen3.7 Plus costs 5.0× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Which is cheaper, o3 or Qwen3.7 Plus?
Qwen3.7 Plus is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; o3 lists at $2 and $8.
Is o3 or Qwen3.7 Plus better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 36.6 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Plus does, with 1M tokens against 200K.
How many benchmarks do o3 and Qwen3.7 Plus share?
27 benchmarks have published results for both models. o3 has 63 scored results on Noometry and Qwen3.7 Plus has 32.