Model comparison
DeepSeek-R1-Distill-Llama-70B vs Kimi K2.7 Code
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 37.8 on the Noometry Index.
Last verified . 2 shared benchmarks.
DeepSeekSummary
- They share 2 benchmarks with published results for both. DeepSeek-R1-Distill-Llama-70B scores higher in 0 categories and Kimi K2.7 Code in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.7 Code leads 53.5 to 30.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 51.4% for DeepSeek-R1-Distill-Llama-70B and 95.6% for Kimi K2.7 Code.
Side by side
| DeepSeek-R1-Distill-Llama-70B | Kimi K2.7 Code | |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Noometry Index | 37.8 | 43.3 |
| Released | 2025-01-20 | 2026-06-12 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.95 |
| Output $ / M tokens | — | $4 |
| Results tracked | 13 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.7 Code leads
DeepSeek-R1-Distill-Llama-70B: 36.8 (#202), Kimi K2.7 Code: 42.9 (#95)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Kimi K2.7 Code |
|---|---|---|
| DeepSWE | — | 30.5% |
| FrontierCode | — | 30.1% |
| LMArena WebDev | — | 1473 |
| SciCode | — | 47.5% |
| WeirdML | — | 54.1% |
| BigCodeBench Instruct | 35.3% | — |
| LiveBench Coding | 51.6% | — |
| BigCodeBench Complete | 49.9% | — |
| ALE-Bench | — | 886.23 |
Agentic & Tool Use Not comparable
DeepSeek-R1-Distill-Llama-70B: —, Kimi K2.7 Code: 24.0 (#122)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Kimi K2.7 Code |
|---|---|---|
| APEX-Agents | — | 37.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 5,083 |
Reasoning Kimi K2.7 Code leads
DeepSeek-R1-Distill-Llama-70B: 24.9 (#156), Kimi K2.7 Code: 39.0 (#61)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Kimi K2.7 Code |
|---|---|---|
| SimpleBench | — | 57.9% |
| Kagi LLM Benchmark | 52.3% | — |
| CritPt | — | 10% |
| Chess Puzzles | — | 21% |
| LiveBench Reasoning | 67.6% | — |
| LiveBench Data Analysis | 55.9% | — |
| Surface Evolver Bench | — | 48.8% |
| Epoch Capabilities Index | — | 149.97 |
| LiveBench | 54.5% | — |
Math Kimi K2.7 Code leads
DeepSeek-R1-Distill-Llama-70B: 36.0 (#176), Kimi K2.7 Code: 52.9 (#48)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Kimi K2.7 Code |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 51.4% | 95.6% |
| FrontierMath (Tiers 1-3) | — | 54% |
| FrontierMath Tier 4 | — | 12.2% |
| LiveBench Math | 58.1% | — |
| MATH Level 5 | 89.9% | — |
Knowledge Kimi K2.7 Code leads
DeepSeek-R1-Distill-Llama-70B: 30.7 (#225), Kimi K2.7 Code: 53.5 (#57)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Kimi K2.7 Code |
|---|---|---|
| GPQA Diamond | 55.7% | 87.9% |
| SimpleQA Verified | — | 36.5% |
Instruction Following Not comparable
DeepSeek-R1-Distill-Llama-70B: 68.2 (#190), Kimi K2.7 Code: —
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Kimi K2.7 Code |
|---|---|---|
| LiveBench Instruction Following | 69.9% | — |
Writing & Preference Not comparable
DeepSeek-R1-Distill-Llama-70B: 49.0 (#194), Kimi K2.7 Code: —
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Kimi K2.7 Code |
|---|---|---|
| LiveBench Language | 23.8% | — |
Frequently asked questions
Is DeepSeek-R1-Distill-Llama-70B better than Kimi K2.7 Code?
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 37.8 on the Noometry Index.
Is DeepSeek-R1-Distill-Llama-70B or Kimi K2.7 Code better for coding?
Kimi K2.7 Code scores higher on coding benchmarks: 42.9 versus 36.8 in the Noometry coding category.
How many benchmarks do DeepSeek-R1-Distill-Llama-70B and Kimi K2.7 Code share?
2 benchmarks have published results for both models. DeepSeek-R1-Distill-Llama-70B has 13 scored results on Noometry and Kimi K2.7 Code has 19.