Model comparison
DeepSeek LLM 67B vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 24.8 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Qwen3.7 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.7 Max leads 61.7 to 7.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 95.6% for Qwen3.7 Max.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Qwen3.7 Max | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 24.8 | 51.4 |
| Released | 2023-11-29 | 2026-05-19 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 131K |
| Input $ / M tokens | — | $2.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 15 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
DeepSeek LLM 67B: 31.3 (#273), Qwen3.7 Max: 50.2 (#43)
| Benchmark | DeepSeek LLM 67B | Qwen3.7 Max |
|---|---|---|
| LMArena Coding | 1096 | 1498 |
| SWE-bench Verified | — | 77.3% |
| LMArena WebDev | — | 1515 |
| SciCode | — | 48.8% |
| ALE-Bench | — | 1,189 |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, Qwen3.7 Max: 21.8 (#129)
| Benchmark | DeepSeek LLM 67B | Qwen3.7 Max |
|---|---|---|
| GBAEval | — | 0.4% |
Reasoning Qwen3.7 Max leads
DeepSeek LLM 67B: 15.9 (#300), Qwen3.7 Max: 48.4 (#36)
| Benchmark | DeepSeek LLM 67B | Qwen3.7 Max |
|---|---|---|
| Chess Puzzles | 0% | 19% |
| LMArena Hard Prompts | 1070 | 1483 |
| Epoch Capabilities Index | 110.54 | 153.74 |
| SimpleBench | — | 70.4% |
| NYT Connections (extended) | — | 85.1% |
| CritPt | — | 13.4% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |
| DTBench | — | 92.3% |
| LMCA | — | 44% |
Math Qwen3.7 Max leads
DeepSeek LLM 67B: 8.1 (#318), Qwen3.7 Max: 62.3 (#26)
| Benchmark | DeepSeek LLM 67B | Qwen3.7 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 95.6% |
| LMArena Math | 1108 | 1488 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| ProofBench | — | 26% |
| MATH Level 5 | 6.4% | — |
Knowledge Qwen3.7 Max leads
DeepSeek LLM 67B: 7.1 (#308), Qwen3.7 Max: 61.7 (#24)
| Benchmark | DeepSeek LLM 67B | Qwen3.7 Max |
|---|---|---|
| GPQA Diamond | 24.6% | 90.9% |
| SimpleQA Verified | — | 55.8% |
| LMArena Expert | — | 1488 |
Multilingual Qwen3.7 Max leads
DeepSeek LLM 67B: 29.5 (#262), Qwen3.7 Max: 57.1 (#13)
| Benchmark | DeepSeek LLM 67B | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1073 | 1475 |
| LMArena Chinese | 1132 | 1533 |
| LMArena Russian | — | 1482 |
Instruction Following Qwen3.7 Max leads
DeepSeek LLM 67B: 55.7 (#272), Qwen3.7 Max: 76.9 (#34)
| Benchmark | DeepSeek LLM 67B | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1079 | 1460 |
Long Context Qwen3.7 Max leads
DeepSeek LLM 67B: 33.1 (#260), Qwen3.7 Max: 45.4 (#34)
| Benchmark | DeepSeek LLM 67B | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1092 | 1484 |
Writing & Preference Qwen3.7 Max leads
DeepSeek LLM 67B: 31.8 (#277), Qwen3.7 Max: 65.2 (#52)
| Benchmark | DeepSeek LLM 67B | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1105 | 1476 |
| LMArena Creative Writing | 1067 | 1450 |
| LMArena Multi-Turn | 1082 | 1482 |
| EQ-Bench 4 | — | 1110 |
Frequently asked questions
Is DeepSeek LLM 67B better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 24.8 on the Noometry Index.
Is DeepSeek LLM 67B or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.2 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Qwen3.7 Max share?
14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Qwen3.7 Max has 33.