Model comparison
DeepSeek-V3.1-Terminus vs Qwen3-Coder 480B-A35B Instruct
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 37.7 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Qwen3-Coder 480B-A35B Instruct in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.3 to 55.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 57.4% for DeepSeek-V3.1-Terminus and 49.5% for Qwen3-Coder 480B-A35B Instruct.
- DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
- Qwen3-Coder 480B-A35B Instruct accepts more context: 262K tokens versus 164K.
Side by side
| DeepSeek-V3.1-Terminus | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.6 | 37.7 |
| Released | 2025-09-22 | 2025-04 |
| Weights | Open | Open |
| Context window | 164K | 262K |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.30 | $1.50 |
| Output $ / M tokens | $1 | $7.50 |
| Results tracked | 16 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 41.5 (#114), Qwen3-Coder 480B-A35B Instruct: 36.2 (#199)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Coding | 1426 | 1413 |
| ALE-Bench | 745.17 | 461.45 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1275 |
| SciCode | 40.6% | — |
| GSO | — | 4.9% |
| WeirdML | — | 41.2% |
| AlgoTune | — | 1.44 |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Qwen3-Coder 480B-A35B Instruct: 23.7 (#116)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), Qwen3-Coder 480B-A35B Instruct: 24.7 (#141)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 49.5% |
| LMArena Hard Prompts | 1427 | 1372 |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math Too close to call
DeepSeek-V3.1-Terminus: 35.7 (#138), Qwen3-Coder 480B-A35B Instruct: 34.9 (#151)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1402 | 1364 |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Qwen3-Coder 480B-A35B Instruct: 36.4 (#159)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | — | 1337 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.3 (#87), Qwen3-Coder 480B-A35B Instruct: 47.8 (#143)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1407 | 1345 |
| LMArena Russian | 1434 | 1367 |
| LMArena Chinese | — | 1356 |
| LMArena French | — | 1394 |
| LMArena German | — | 1324 |
| LMArena Japanese | — | 1309 |
| LMArena Korean | — | 1307 |
| LMArena Spanish | — | 1360 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.4 (#96), Qwen3-Coder 480B-A35B Instruct: 71.8 (#142)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1406 | 1356 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.5 (#88), Qwen3-Coder 480B-A35B Instruct: 42.0 (#126)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1426 | 1379 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), Qwen3-Coder 480B-A35B Instruct: 55.5 (#142)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1420 | 1356 |
| LMArena Creative Writing | 1404 | 1333 |
| LMArena Multi-Turn | 1411 | 1365 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Qwen3-Coder 480B-A35B Instruct?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 37.7 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1-Terminus or Qwen3-Coder 480B-A35B Instruct?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.
Is DeepSeek-V3.1-Terminus or Qwen3-Coder 480B-A35B Instruct better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 36.2 in the Noometry coding category.
Which has the bigger context window?
Qwen3-Coder 480B-A35B Instruct does, with 262K tokens against 164K.
How many benchmarks do DeepSeek-V3.1-Terminus and Qwen3-Coder 480B-A35B Instruct share?
12 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.