Model comparison
GPT-5.6 Terra vs Qwen3.7 Max
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 51.5 on the Noometry Index.
Last verified . 30 shared benchmarks.
Alibaba (Qwen)Summary
- They share 30 benchmarks with published results for both. GPT-5.6 Terra scores higher in 5 categories and Qwen3.7 Max in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Terra leads 81.6 to 62.4.
- The biggest single-benchmark swing is ProofBench: 74% for GPT-5.6 Terra and 26% for Qwen3.7 Max.
- Qwen3.7 Max is cheaper at $2.50 / $7.50 per million input/output tokens, against $2 / $12 for GPT-5.6 Terra.
- GPT-5.6 Terra accepts more context: 1.05M tokens versus 1M.
Side by side
| GPT-5.6 Terra | Qwen3.7 Max | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 59.2 | 51.5 |
| Released | 2026-07-09 | 2026-05-19 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 128K | 131K |
| Input $ / M tokens | $2 | $2.50 |
| Output $ / M tokens | $12 | $7.50 |
| Results tracked | 52 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Terra leads
GPT-5.6 Terra: 57.7 (#19), Qwen3.7 Max: 50.4 (#45)
| Benchmark | GPT-5.6 Terra | Qwen3.7 Max |
|---|---|---|
| LMArena WebDev | 1522 | 1515 |
| SciCode | 55% | 48.8% |
| LMArena Coding | 1484 | 1498 |
| ALE-Bench | 1,951 | 1,189 |
| SWE-bench Verified | — | 77.3% |
| DeepSWE | 69.6% | — |
| FrontierCode | 41.3% | — |
| CursorBench | 41.3% | — |
| WeirdML | 78.3% | — |
Agentic & Tool Use GPT-5.6 Terra leads
GPT-5.6 Terra: 40.1 (#25), Qwen3.7 Max: 22.1 (#135)
| Benchmark | GPT-5.6 Terra | Qwen3.7 Max |
|---|---|---|
| APEX-Agents | 58.2% | — |
| BALROG | 53.2% | — |
| GBAEval | — | 0.4% |
| GDP.pdf | 24.7% | — |
| Vending-Bench 2 | 7,343 | — |
Reasoning GPT-5.6 Terra leads
GPT-5.6 Terra: 60.7 (#21), Qwen3.7 Max: 49.2 (#38)
| Benchmark | GPT-5.6 Terra | Qwen3.7 Max |
|---|---|---|
| SimpleBench | 48.9% | 70.4% |
| NYT Connections (extended) | 78.4% | 85.1% |
| CritPt | 30% | 13.4% |
| Chess Puzzles | 54% | 19% |
| LMArena Hard Prompts | 1468 | 1483 |
| Mystery Game Puzzles | 35% | 32% |
| DTBench | 93.3% | 92.3% |
| LMCA | 55% | 44% |
| Epoch Capabilities Index | 159.62 | 153.68 |
| ARC-AGI-2 | 83.9% | — |
| Kagi LLM Benchmark | 51.3% | — |
| ARC-AGI-1 | 96.5% | — |
| EBR-Bench | — | 9.5% |
| Surface Evolver Bench | 83.8% | — |
Math GPT-5.6 Terra leads
GPT-5.6 Terra: 81.6 (#12), Qwen3.7 Max: 62.4 (#32)
| Benchmark | GPT-5.6 Terra | Qwen3.7 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 86% | 64.6% |
| FrontierMath Tier 4 | 70.7% | 34.1% |
| OTIS Mock AIME 2024-2025 | 99.7% | 95.6% |
| ProofBench | 74% | 26% |
| LMArena Math | 1466 | 1490 |
Knowledge Too close to call
GPT-5.6 Terra: 61.2 (#30), Qwen3.7 Max: 61.6 (#28)
| Benchmark | GPT-5.6 Terra | Qwen3.7 Max |
|---|---|---|
| GPQA Diamond | 93.3% | 90.9% |
| SimpleQA Verified | 43.2% | 55.8% |
| LMArena Expert | 1492 | 1488 |
Multimodal Not comparable
GPT-5.6 Terra: 47.3 (#11), Qwen3.7 Max: —
| Benchmark | GPT-5.6 Terra | Qwen3.7 Max |
|---|---|---|
| LMArena Vision | 1271 | — |
| Blueprint-Bench 2 | 30.8% | — |
| Furniture Assembly | 54.2% | — |
| LMArena Document | 1472 | — |
Multilingual Qwen3.7 Max leads
GPT-5.6 Terra: 54.4 (#44), Qwen3.7 Max: 56.9 (#15)
| Benchmark | GPT-5.6 Terra | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1439 | 1474 |
| LMArena Chinese | 1513 | 1530 |
| LMArena Russian | 1450 | 1484 |
| LMArena French | 1471 | — |
| LMArena German | 1460 | — |
| LMArena Japanese | 1457 | — |
| LMArena Korean | 1425 | — |
| LMArena Spanish | 1448 | — |
Instruction Following Too close to call
GPT-5.6 Terra: 76.4 (#40), Qwen3.7 Max: 76.7 (#38)
| Benchmark | GPT-5.6 Terra | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1454 | 1460 |
Long Context Qwen3.7 Max leads
GPT-5.6 Terra: 44.4 (#68), Qwen3.7 Max: 45.4 (#40)
| Benchmark | GPT-5.6 Terra | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1451 | 1482 |
Writing & Preference GPT-5.6 Terra leads
GPT-5.6 Terra: 70.2 (#23), Qwen3.7 Max: 65.0 (#54)
| Benchmark | GPT-5.6 Terra | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1447 | 1476 |
| LMArena Creative Writing | 1410 | 1449 |
| EQ-Bench 4 | 1234 | 1110 |
| LMArena Multi-Turn | 1449 | 1481 |
| EQ-Bench Creative Writing | 1855 | — |
Frequently asked questions
Is GPT-5.6 Terra better than Qwen3.7 Max?
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 51.5 on the Noometry Index.
Which is cheaper, GPT-5.6 Terra or Qwen3.7 Max?
Qwen3.7 Max is cheaper. It lists at $2.50 per million input tokens and $7.50 per million output tokens; GPT-5.6 Terra lists at $2 and $12.
Is GPT-5.6 Terra or Qwen3.7 Max better for coding?
GPT-5.6 Terra scores higher on coding benchmarks: 57.7 versus 50.4 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Terra does, with 1.05M tokens against 1M.
How many benchmarks do GPT-5.6 Terra and Qwen3.7 Max share?
30 benchmarks have published results for both models. GPT-5.6 Terra has 52 scored results on Noometry and Qwen3.7 Max has 33.