Model comparison
DeepSeek-R1-Distill-Llama-70B vs Qwen3 8B
DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.8 to 33.7 on the Noometry Index.
Last verified . 2 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. DeepSeek-R1-Distill-Llama-70B scores higher in 3 categories and Qwen3 8B in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-R1-Distill-Llama-70B leads 24.9 to 16.6.
Side by side
| DeepSeek-R1-Distill-Llama-70B | Qwen3 8B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.8 | 33.7 |
| Released | 2025-01-20 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.18 |
| Output $ / M tokens | — | $0.70 |
| Results tracked | 13 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 36.8 (#202), Qwen3 8B: 34.0 (#248)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Qwen3 8B |
|---|---|---|
| SciCode | — | 22.6% |
| BigCodeBench Instruct | 35.3% | — |
| LiveBench Coding | 51.6% | — |
| BigCodeBench Complete | 49.9% | — |
Agentic & Tool Use Not comparable
DeepSeek-R1-Distill-Llama-70B: —, Qwen3 8B: 30.2 (#78)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 42.6% |
Reasoning DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 24.9 (#156), Qwen3 8B: 16.6 (#303)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Qwen3 8B |
|---|---|---|
| Kagi LLM Benchmark | 52.3% | — |
| CritPt | — | 0% |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | 67.6% | — |
| DTBench | — | 59.7% |
| LiveBench Data Analysis | 55.9% | — |
| LMCA | — | 8.8% |
| Epoch Capabilities Index | — | 136.17 |
| LiveBench | 54.5% | — |
Math DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 36.0 (#176), Qwen3 8B: 34.9 (#191)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 51.4% | 56.1% |
| LiveBench Math | 58.1% | — |
| MATH Level 5 | 89.9% | — |
Knowledge Qwen3 8B leads
DeepSeek-R1-Distill-Llama-70B: 30.7 (#225), Qwen3 8B: 36.1 (#173)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Qwen3 8B |
|---|---|---|
| GPQA Diamond | 55.7% | 56.8% |
| Vectara Hallucination Rate | — | 4.8% |
Instruction Following Not comparable
DeepSeek-R1-Distill-Llama-70B: 68.2 (#190), Qwen3 8B: —
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Qwen3 8B |
|---|---|---|
| LiveBench Instruction Following | 69.9% | — |
Long Context Not comparable
DeepSeek-R1-Distill-Llama-70B: —, Qwen3 8B: 37.9 (#210)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |
Writing & Preference Not comparable
DeepSeek-R1-Distill-Llama-70B: 49.0 (#194), Qwen3 8B: —
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Qwen3 8B |
|---|---|---|
| LiveBench Language | 23.8% | — |
Frequently asked questions
Is DeepSeek-R1-Distill-Llama-70B better than Qwen3 8B?
DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.8 to 33.7 on the Noometry Index.
Is DeepSeek-R1-Distill-Llama-70B or Qwen3 8B better for coding?
DeepSeek-R1-Distill-Llama-70B scores higher on coding benchmarks: 36.8 versus 34.0 in the Noometry coding category.
How many benchmarks do DeepSeek-R1-Distill-Llama-70B and Qwen3 8B share?
2 benchmarks have published results for both models. DeepSeek-R1-Distill-Llama-70B has 13 scored results on Noometry and Qwen3 8B has 11.