Model comparison
DeepSeek LLM 67B vs Kimi K2.5 Instant
Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeekSummary
- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Kimi K2.5 Instant in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.5 Instant leads 40.2 to 7.0.
Side by side
| DeepSeek LLM 67B | Kimi K2.5 Instant | |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Noometry Index | 24.9 | 43.6 |
| Released | 2023-11-29 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 Instant leads
DeepSeek LLM 67B: 31.9 (#278), Kimi K2.5 Instant: 42.6 (#97)
| Benchmark | DeepSeek LLM 67B | Kimi K2.5 Instant |
|---|---|---|
| LMArena Coding | 1096 | 1484 |
| LMArena WebDev | — | 1404 |
Reasoning Kimi K2.5 Instant leads
DeepSeek LLM 67B: 16.5 (#304), Kimi K2.5 Instant: 29.7 (#90)
| Benchmark | DeepSeek LLM 67B | Kimi K2.5 Instant |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1443 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
Math Kimi K2.5 Instant leads
DeepSeek LLM 67B: 8.7 (#324), Kimi K2.5 Instant: 39.4 (#105)
| Benchmark | DeepSeek LLM 67B | Kimi K2.5 Instant |
|---|---|---|
| LMArena Math | 1108 | 1442 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge Kimi K2.5 Instant leads
DeepSeek LLM 67B: 7.0 (#313), Kimi K2.5 Instant: 40.2 (#123)
| Benchmark | DeepSeek LLM 67B | Kimi K2.5 Instant |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1440 |
Multimodal Not comparable
DeepSeek LLM 67B: —, Kimi K2.5 Instant: 40.2 (#50)
| Benchmark | DeepSeek LLM 67B | Kimi K2.5 Instant |
|---|---|---|
| LMArena Vision | — | 1254 |
Multilingual Kimi K2.5 Instant leads
DeepSeek LLM 67B: 29.4 (#267), Kimi K2.5 Instant: 52.0 (#94)
| Benchmark | DeepSeek LLM 67B | Kimi K2.5 Instant |
|---|---|---|
| LMArena Non-English | 1073 | 1406 |
| LMArena Chinese | 1132 | 1449 |
| LMArena French | — | 1403 |
| LMArena German | — | 1413 |
| LMArena Korean | — | 1378 |
| LMArena Russian | — | 1404 |
| LMArena Spanish | — | 1447 |
Instruction Following Kimi K2.5 Instant leads
DeepSeek LLM 67B: 55.4 (#277), Kimi K2.5 Instant: 75.3 (#65)
| Benchmark | DeepSeek LLM 67B | Kimi K2.5 Instant |
|---|---|---|
| LMArena Instruction Following | 1079 | 1430 |
Long Context Kimi K2.5 Instant leads
DeepSeek LLM 67B: 33.1 (#265), Kimi K2.5 Instant: 43.9 (#83)
| Benchmark | DeepSeek LLM 67B | Kimi K2.5 Instant |
|---|---|---|
| LMArena Longer Query | 1092 | 1435 |
Writing & Preference Kimi K2.5 Instant leads
DeepSeek LLM 67B: 31.6 (#282), Kimi K2.5 Instant: 60.6 (#95)
| Benchmark | DeepSeek LLM 67B | Kimi K2.5 Instant |
|---|---|---|
| LMArena Text | 1105 | 1420 |
| LMArena Creative Writing | 1067 | 1381 |
| LMArena Multi-Turn | 1082 | 1427 |
Frequently asked questions
Is DeepSeek LLM 67B better than Kimi K2.5 Instant?
Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Kimi K2.5 Instant better for coding?
Kimi K2.5 Instant scores higher on coding benchmarks: 42.6 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Kimi K2.5 Instant share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Kimi K2.5 Instant has 18.