Model comparison
DeepSeek-R1 vs Qwen3-Next 80B-A3B Instruct
DeepSeek-R1 and Qwen3-Next 80B-A3B Instruct score almost the same on the Noometry Index (42.0 vs 42.5), so choose on price, context window or the category you care about most.
Last verified . 25 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. DeepSeek-R1 scores higher in 7 categories and Qwen3-Next 80B-A3B Instruct in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3-Next 80B-A3B Instruct leads 30.1 to 18.7.
- The biggest single-benchmark swing is Fiction.LiveBench: 75% for DeepSeek-R1 and 55.6% for Qwen3-Next 80B-A3B Instruct.
- Both cost about the same: $0.50 input and $2.15 output per million tokens.
- DeepSeek-R1 accepts more context: 164K tokens versus 131K.
- Qwen3-Next 80B-A3B Instruct has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-R1 | Qwen3-Next 80B-A3B Instruct | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.0 | 42.5 |
| Released | 2025-01-20 | 2025-09 |
| Weights | Proprietary | Open |
| Context window | 164K | 131K |
| Max output | 64K | 33K |
| Input $ / M tokens | $0.50 | $0.50 |
| Output $ / M tokens | $2.15 | $2 |
| Results tracked | 52 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1 leads
DeepSeek-R1: 45.9 (#63), Qwen3-Next 80B-A3B Instruct: 41.9 (#101)
| Benchmark | DeepSeek-R1 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Coding | 1427 | 1441 |
| Aider Polyglot | 71.4% | — |
| SciCode | 35.7% | — |
| WeirdML | 41.6% | — |
| LiveBench Coding | 66.7% | — |
| ALE-Bench | 804.12 | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use Not comparable
DeepSeek-R1: 30.4 (#68), Qwen3-Next 80B-A3B Instruct: —
| Benchmark | DeepSeek-R1 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
Reasoning Qwen3-Next 80B-A3B Instruct leads
DeepSeek-R1: 18.7 (#253), Qwen3-Next 80B-A3B Instruct: 30.1 (#79)
| Benchmark | DeepSeek-R1 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 69.4% | 66.7% |
| LMArena Hard Prompts | 1415 | 1428 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| ARC-AGI-1 | 21.2% | — |
| CritPt | 1.1% | — |
| LiveBench Reasoning | 83.2% | — |
| LiveBench Data Analysis | 69.8% | — |
| Epoch Capabilities Index | 141.3 | — |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math DeepSeek-R1 leads
DeepSeek-R1: 42.0 (#70), Qwen3-Next 80B-A3B Instruct: 36.3 (#118)
| Benchmark | DeepSeek-R1 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Omni-MATH | 42.4% | 46.7% |
| LMArena Math | 1401 | 1440 |
| OTIS Mock AIME 2024-2025 | 66.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |
Knowledge DeepSeek-R1 leads
DeepSeek-R1: 44.3 (#81), Qwen3-Next 80B-A3B Instruct: 41.3 (#102)
| Benchmark | DeepSeek-R1 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| MMLU-Pro | 79.3% | 78.6% |
| Vectara Hallucination Rate | 11.3% | 9.3% |
| GPQA (HELM) | 66.6% | 63% |
| LMArena Expert | 1394 | 1416 |
| GPQA Diamond | 76.3% | — |
| Confabulations | 12.7% | — |
Multilingual Too close to call
DeepSeek-R1: 52.6 (#80), Qwen3-Next 80B-A3B Instruct: 52.3 (#88)
| Benchmark | DeepSeek-R1 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Non-English | 1412 | 1407 |
| LMArena Chinese | 1443 | 1461 |
| LMArena French | 1415 | 1415 |
| LMArena German | 1405 | 1416 |
| LMArena Japanese | 1394 | 1398 |
| LMArena Korean | 1359 | 1366 |
| LMArena Russian | 1423 | 1403 |
| LMArena Spanish | 1410 | 1436 |
Instruction Following DeepSeek-R1 leads
DeepSeek-R1: 72.2 (#138), Qwen3-Next 80B-A3B Instruct: 71.0 (#154)
| Benchmark | DeepSeek-R1 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| IFEval | 78.4% | 81% |
| LMArena Instruction Following | 1382 | 1388 |
| LiveBench Instruction Following | 80.5% | — |
Long Context DeepSeek-R1 leads
DeepSeek-R1: 45.4 (#36), Qwen3-Next 80B-A3B Instruct: 37.0 (#218)
| Benchmark | DeepSeek-R1 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Fiction.LiveBench | 75% | 55.6% |
| LMArena Longer Query | 1391 | 1403 |
Writing & Preference DeepSeek-R1 leads
DeepSeek-R1: 61.5 (#84), Qwen3-Next 80B-A3B Instruct: 58.2 (#116)
| Benchmark | DeepSeek-R1 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Text | 1428 | 1417 |
| LMArena Creative Writing | 1406 | 1333 |
| WildBench | 82.8% | 80.7% |
| LMArena Multi-Turn | 1404 | 1415 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than Qwen3-Next 80B-A3B Instruct?
DeepSeek-R1 and Qwen3-Next 80B-A3B Instruct score almost the same on the Noometry Index (42.0 vs 42.5), so choose on price, context window or the category you care about most.
Which is cheaper, DeepSeek-R1 or Qwen3-Next 80B-A3B Instruct?
Qwen3-Next 80B-A3B Instruct is cheaper. It lists at $0.50 per million input tokens and $2 per million output tokens; DeepSeek-R1 lists at $0.50 and $2.15.
Is DeepSeek-R1 or Qwen3-Next 80B-A3B Instruct better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 45.9 versus 41.9 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-R1 does, with 164K tokens against 131K.
How many benchmarks do DeepSeek-R1 and Qwen3-Next 80B-A3B Instruct share?
25 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.