Model comparison
GPT-5.6 Terra vs Qwen3-Coder 480B-A35B Instruct
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 38.1 on the Noometry Index. Qwen3-Coder 480B-A35B Instruct costs 1.5× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. GPT-5.6 Terra scores higher in 9 categories and Qwen3-Coder 480B-A35B Instruct in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Terra leads 81.6 to 37.6.
- The biggest single-benchmark swing is WeirdML: 78.3% for GPT-5.6 Terra and 41.2% for Qwen3-Coder 480B-A35B Instruct.
- Qwen3-Coder 480B-A35B Instruct is cheaper at $1.50 / $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 262K.
- Qwen3-Coder 480B-A35B Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-5.6 Terra | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 59.2 | 38.1 |
| Released | 2026-07-09 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 66K |
| Input $ / M tokens | $2 | $1.50 |
| Output $ / M tokens | $12 | $7.50 |
| Results tracked | 52 | 25 |
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-Coder 480B-A35B Instruct: 35.5 (#223)
| Benchmark | GPT-5.6 Terra | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena WebDev | 1522 | 1275 |
| WeirdML | 78.3% | 41.2% |
| LMArena Coding | 1484 | 1412 |
| ALE-Bench | 1,951 | 461.45 |
| DeepSWE | 69.6% | — |
| FrontierCode | 41.3% | — |
| SWE-bench Verified (bash only) | — | 55.4% |
| CursorBench | 41.3% | — |
| SciCode | 55% | — |
| GSO | — | 4.9% |
| AlgoTune | — | 1.44 |
Agentic & Tool Use GPT-5.6 Terra leads
GPT-5.6 Terra: 40.1 (#25), Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)
| Benchmark | GPT-5.6 Terra | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| APEX-Agents | 58.2% | — |
| BALROG | 53.2% | — |
| GDP.pdf | 24.7% | — |
| Vending-Bench 2 | 7,343 | — |
Reasoning GPT-5.6 Terra leads
GPT-5.6 Terra: 60.7 (#21), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)
| Benchmark | GPT-5.6 Terra | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 51.3% | 49.5% |
| LMArena Hard Prompts | 1468 | 1372 |
| ARC-AGI-2 | 83.9% | — |
| SimpleBench | 48.9% | — |
| NYT Connections (extended) | 78.4% | — |
| ARC-AGI-1 | 96.5% | — |
| CritPt | 30% | — |
| Chess Puzzles | 54% | — |
| Mystery Game Puzzles | 35% | — |
| DTBench | 93.3% | — |
| LMCA | 55% | — |
| Surface Evolver Bench | 83.8% | — |
| Epoch Capabilities Index | 159.62 | — |
Math GPT-5.6 Terra leads
GPT-5.6 Terra: 81.6 (#12), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)
| Benchmark | GPT-5.6 Terra | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1466 | 1365 |
| FrontierMath (Tiers 1-3) | 86% | — |
| FrontierMath Tier 4 | 70.7% | — |
| OTIS Mock AIME 2024-2025 | 99.7% | — |
| ProofBench | 74% | — |
Knowledge GPT-5.6 Terra leads
GPT-5.6 Terra: 61.2 (#30), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)
| Benchmark | GPT-5.6 Terra | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1492 | 1338 |
| GPQA Diamond | 93.3% | — |
| SimpleQA Verified | 43.2% | — |
Multimodal Not comparable
GPT-5.6 Terra: 47.3 (#11), Qwen3-Coder 480B-A35B Instruct: —
| Benchmark | GPT-5.6 Terra | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Vision | 1271 | — |
| Blueprint-Bench 2 | 30.8% | — |
| Furniture Assembly | 54.2% | — |
| LMArena Document | 1472 | — |
Multilingual GPT-5.6 Terra leads
GPT-5.6 Terra: 54.4 (#44), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)
| Benchmark | GPT-5.6 Terra | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1439 | 1346 |
| LMArena Chinese | 1513 | 1357 |
| LMArena French | 1471 | 1398 |
| LMArena German | 1460 | 1325 |
| LMArena Japanese | 1457 | 1310 |
| LMArena Korean | 1425 | 1305 |
| LMArena Russian | 1450 | 1366 |
| LMArena Spanish | 1448 | 1360 |
Instruction Following GPT-5.6 Terra leads
GPT-5.6 Terra: 76.4 (#40), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)
| Benchmark | GPT-5.6 Terra | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1454 | 1355 |
Long Context GPT-5.6 Terra leads
GPT-5.6 Terra: 44.4 (#68), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)
| Benchmark | GPT-5.6 Terra | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1451 | 1378 |
Writing & Preference GPT-5.6 Terra leads
GPT-5.6 Terra: 70.2 (#23), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)
| Benchmark | GPT-5.6 Terra | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1447 | 1357 |
| LMArena Creative Writing | 1410 | 1333 |
| LMArena Multi-Turn | 1449 | 1365 |
| EQ-Bench Creative Writing | 1855 | — |
| EQ-Bench 4 | 1234 | — |
Frequently asked questions
Is GPT-5.6 Terra better than Qwen3-Coder 480B-A35B Instruct?
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 38.1 on the Noometry Index. Qwen3-Coder 480B-A35B Instruct costs 1.5× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.
Which is cheaper, GPT-5.6 Terra or Qwen3-Coder 480B-A35B Instruct?
Qwen3-Coder 480B-A35B Instruct is cheaper. It lists at $1.50 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-Coder 480B-A35B Instruct better for coding?
GPT-5.6 Terra scores higher on coding benchmarks: 57.7 versus 35.5 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Terra does, with 1.05M tokens against 262K.
How many benchmarks do GPT-5.6 Terra and Qwen3-Coder 480B-A35B Instruct share?
21 benchmarks have published results for both models. GPT-5.6 Terra has 52 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.