Model comparison
DeepSeek-V3.1-Terminus vs Qwen3-30B-A3B
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 2.1× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 15 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Qwen3-30B-A3B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where DeepSeek-V3.1-Terminus leads 43.4 to 31.0.
- The biggest single-benchmark swing is DTBench: 81.3% for DeepSeek-V3.1-Terminus and 69.3% for Qwen3-30B-A3B.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $0.27 / $1 for DeepSeek-V3.1-Terminus.
- DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 41K.
Side by side
| DeepSeek-V3.1-Terminus | Qwen3-30B-A3B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 43.1 | 38.9 |
| Released | 2025-09-22 | 2025-04-28 |
| Weights | Open | Open |
| Context window | 164K | 41K |
| Max output | 147K | 16K |
| Input $ / M tokens | $0.27 | $0.12 |
| Output $ / M tokens | $1 | $0.50 |
| Results tracked | 16 | 32 |
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: 42.0 (#113), Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3-30B-A3B |
|---|---|---|
| SciCode | 40.6% | 33.3% |
| LMArena Coding | 1426 | 1416 |
| WeirdML | — | 29.8% |
| ALE-Bench | 745.17 | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 26.4 (#133), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3-30B-A3B |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 54.9% |
| CritPt | 1.7% | 0.3% |
| LMArena Hard Prompts | 1426 | 1398 |
| DTBench | 81.3% | 69.3% |
| LMCA | 28.6% | 22.4% |
| Chess Puzzles | — | 8% |
| Epoch Capabilities Index | — | 139.63 |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 38.5 (#137), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3-30B-A3B |
|---|---|---|
| LMArena Math | 1402 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | — | 70.1% |
| Confabulations | — | 12.3% |
| LMArena Expert | — | 1396 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1407 | 1372 |
| LMArena Russian | 1436 | 1370 |
| LMArena Chinese | — | 1433 |
| LMArena French | — | 1418 |
| LMArena German | — | 1380 |
| LMArena Japanese | — | 1337 |
| LMArena Korean | — | 1331 |
| LMArena Spanish | — | 1404 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1404 | 1363 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1421 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1419 | 1384 |
| LMArena Creative Writing | 1403 | 1317 |
| LMArena Multi-Turn | 1411 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Qwen3-30B-A3B?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 2.1× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1-Terminus or Qwen3-30B-A3B?
Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; DeepSeek-V3.1-Terminus lists at $0.27 and $1.
Is DeepSeek-V3.1-Terminus or Qwen3-30B-A3B better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 37.5 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.1-Terminus does, with 164K tokens against 41K.
How many benchmarks do DeepSeek-V3.1-Terminus and Qwen3-30B-A3B share?
15 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Qwen3-30B-A3B has 32.