Model comparison
DeepSeek LLM 67B vs Kimi K2.5
Kimi K2.5 is the stronger model overall, scoring 48.1 to 24.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeekSummary
- They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Kimi K2.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.5 leads 53.6 to 7.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 92.2% for Kimi K2.5.
Side by side
| DeepSeek LLM 67B | Kimi K2.5 | |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Noometry Index | 24.9 | 48.1 |
| Released | 2023-11-29 | 2026-01-27 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.45 |
| Output $ / M tokens | — | $2.25 |
| Results tracked | 15 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
DeepSeek LLM 67B: 31.9 (#278), Kimi K2.5: 48.8 (#53)
| Benchmark | DeepSeek LLM 67B | Kimi K2.5 |
|---|---|---|
| LMArena Coding | 1096 | 1474 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 70.8% |
| LMArena WebDev | — | 1437 |
| SWE-bench Multilingual | — | 67.3% |
| SciCode | — | 49% |
| WeirdML | — | 45.6% |
| ALE-Bench | — | 821.65 |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, Kimi K2.5: 34.2 (#48)
| Benchmark | DeepSeek LLM 67B | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | — | 43.2% |
| OSWorld | — | 63.3% |
| Vending-Bench 2 | — | 1,198 |
Reasoning Kimi K2.5 leads
DeepSeek LLM 67B: 16.5 (#304), Kimi K2.5: 31.2 (#80)
| Benchmark | DeepSeek LLM 67B | Kimi K2.5 |
|---|---|---|
| Chess Puzzles | 0% | 12% |
| LMArena Hard Prompts | 1070 | 1453 |
| Epoch Capabilities Index | 110.5 | 148.03 |
| ARC-AGI-2 | — | 11.8% |
| SimpleBench | — | 46.8% |
| Kagi LLM Benchmark | — | 78.5% |
| NYT Connections (extended) | — | 69.9% |
| ARC-AGI-1 | — | 65.3% |
| CritPt | — | 3.1% |
| EnigmaEval | — | 3.4% |
| Thematic Generalization | — | 69.4% |
Math Kimi K2.5 leads
DeepSeek LLM 67B: 8.7 (#324), Kimi K2.5: 51.8 (#53)
| Benchmark | DeepSeek LLM 67B | Kimi K2.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 92.2% |
| LMArena Math | 1108 | 1470 |
| MathArena Final-Answer Competitions | — | 62.3% |
| MATH Level 5 | 6.4% | — |
| FrontierMath (Feb 2025 set) | — | 27.9% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Kimi K2.5 leads
DeepSeek LLM 67B: 7.0 (#313), Kimi K2.5: 53.6 (#56)
| Benchmark | DeepSeek LLM 67B | Kimi K2.5 |
|---|---|---|
| GPQA Diamond | 24.6% | 87.6% |
| Humanity's Last Exam | — | 24.4% |
| SimpleQA Verified | — | 34.3% |
| Vectara Hallucination Rate | — | 14.2% |
| LMArena Expert | — | 1466 |
Multimodal Not comparable
DeepSeek LLM 67B: —, Kimi K2.5: 41.1 (#39)
| Benchmark | DeepSeek LLM 67B | Kimi K2.5 |
|---|---|---|
| LMArena Vision | — | 1269 |
| LMArena Document | — | 1430 |
Multilingual Kimi K2.5 leads
DeepSeek LLM 67B: 29.4 (#267), Kimi K2.5: 53.9 (#53)
| Benchmark | DeepSeek LLM 67B | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1073 | 1433 |
| LMArena Chinese | 1132 | 1495 |
| LMArena French | — | 1454 |
| LMArena German | — | 1441 |
| LMArena Japanese | — | 1421 |
| LMArena Korean | — | 1410 |
| LMArena Russian | — | 1435 |
| LMArena Spanish | — | 1450 |
Instruction Following Kimi K2.5 leads
DeepSeek LLM 67B: 55.4 (#277), Kimi K2.5: 75.3 (#64)
| Benchmark | DeepSeek LLM 67B | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1431 |
Long Context Kimi K2.5 leads
DeepSeek LLM 67B: 33.1 (#265), Kimi K2.5: 52.1 (#7)
| Benchmark | DeepSeek LLM 67B | Kimi K2.5 |
|---|---|---|
| LMArena Longer Query | 1092 | 1445 |
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |
Writing & Preference Kimi K2.5 leads
DeepSeek LLM 67B: 31.6 (#282), Kimi K2.5: 65.1 (#53)
| Benchmark | DeepSeek LLM 67B | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1105 | 1445 |
| LMArena Creative Writing | 1067 | 1423 |
| LMArena Multi-Turn | 1082 | 1444 |
| EQ-Bench Creative Writing | — | 1579 |
Frequently asked questions
Is DeepSeek LLM 67B better than Kimi K2.5?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Kimi K2.5 better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Kimi K2.5 share?
14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Kimi K2.5 has 51.