Model comparison
DeepSeek LLM 67B vs Kimi K2.7 Code
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 24.9 on the Noometry Index.
Last verified . 4 shared benchmarks.
DeepSeekSummary
- They share 4 benchmarks with published results for both. DeepSeek LLM 67B 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 7.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 95.6% for Kimi K2.7 Code.
Side by side
| DeepSeek LLM 67B | Kimi K2.7 Code | |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Noometry Index | 24.9 | 43.3 |
| Released | 2023-11-29 | 2026-06-12 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.95 |
| Output $ / M tokens | — | $4 |
| Results tracked | 15 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.7 Code leads
DeepSeek LLM 67B: 31.9 (#278), Kimi K2.7 Code: 42.9 (#95)
| Benchmark | DeepSeek LLM 67B | Kimi K2.7 Code |
|---|---|---|
| DeepSWE | — | 30.5% |
| FrontierCode | — | 30.1% |
| LMArena WebDev | — | 1473 |
| SciCode | — | 47.5% |
| WeirdML | — | 54.1% |
| LMArena Coding | 1096 | — |
| ALE-Bench | — | 886.23 |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, Kimi K2.7 Code: 24.0 (#122)
| Benchmark | DeepSeek LLM 67B | Kimi K2.7 Code |
|---|---|---|
| APEX-Agents | — | 37.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 5,083 |
Reasoning Kimi K2.7 Code leads
DeepSeek LLM 67B: 16.5 (#304), Kimi K2.7 Code: 39.0 (#61)
| Benchmark | DeepSeek LLM 67B | Kimi K2.7 Code |
|---|---|---|
| Chess Puzzles | 0% | 21% |
| Epoch Capabilities Index | 110.5 | 149.97 |
| SimpleBench | — | 57.9% |
| CritPt | — | 10% |
| LMArena Hard Prompts | 1070 | — |
| Surface Evolver Bench | — | 48.8% |
Math Kimi K2.7 Code leads
DeepSeek LLM 67B: 8.7 (#324), Kimi K2.7 Code: 52.9 (#48)
| Benchmark | DeepSeek LLM 67B | Kimi K2.7 Code |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 95.6% |
| FrontierMath (Tiers 1-3) | — | 54% |
| FrontierMath Tier 4 | — | 12.2% |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |
Knowledge Kimi K2.7 Code leads
DeepSeek LLM 67B: 7.0 (#313), Kimi K2.7 Code: 53.5 (#57)
| Benchmark | DeepSeek LLM 67B | Kimi K2.7 Code |
|---|---|---|
| GPQA Diamond | 24.6% | 87.9% |
| SimpleQA Verified | — | 36.5% |
Multilingual Not comparable
DeepSeek LLM 67B: 29.4 (#267), Kimi K2.7 Code: —
| Benchmark | DeepSeek LLM 67B | Kimi K2.7 Code |
|---|---|---|
| LMArena Non-English | 1073 | — |
| LMArena Chinese | 1132 | — |
Instruction Following Not comparable
DeepSeek LLM 67B: 55.4 (#277), Kimi K2.7 Code: —
| Benchmark | DeepSeek LLM 67B | Kimi K2.7 Code |
|---|---|---|
| LMArena Instruction Following | 1079 | — |
Long Context Not comparable
DeepSeek LLM 67B: 33.1 (#265), Kimi K2.7 Code: —
| Benchmark | DeepSeek LLM 67B | Kimi K2.7 Code |
|---|---|---|
| LMArena Longer Query | 1092 | — |
Writing & Preference Not comparable
DeepSeek LLM 67B: 31.6 (#282), Kimi K2.7 Code: —
| Benchmark | DeepSeek LLM 67B | Kimi K2.7 Code |
|---|---|---|
| LMArena Text | 1105 | — |
| LMArena Creative Writing | 1067 | — |
| LMArena Multi-Turn | 1082 | — |
Frequently asked questions
Is DeepSeek LLM 67B better than Kimi K2.7 Code?
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Kimi K2.7 Code better for coding?
Kimi K2.7 Code scores higher on coding benchmarks: 42.9 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Kimi K2.7 Code share?
4 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Kimi K2.7 Code has 19.