Model comparison
DeepSeek-V2.5 (Sep 2024) vs Kimi K2.5 Instant
Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 37.6 on the Noometry Index.
Last verified . 16 shared benchmarks.
DeepSeekSummary
- They share 16 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) 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 coding, where Kimi K2.5 Instant leads 42.6 to 31.7.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Kimi K2.5 Instant | |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Noometry Index | 37.6 | 43.6 |
| Released | 2024-09-06 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 Instant leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Kimi K2.5 Instant: 42.6 (#97)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2.5 Instant |
|---|---|---|
| LMArena Coding | 1309 | 1484 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1404 |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning Kimi K2.5 Instant leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Kimi K2.5 Instant: 29.7 (#90)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2.5 Instant |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1443 |
Math Kimi K2.5 Instant leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Kimi K2.5 Instant: 39.4 (#105)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2.5 Instant |
|---|---|---|
| LMArena Math | 1288 | 1442 |
Knowledge Kimi K2.5 Instant leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Kimi K2.5 Instant: 40.2 (#123)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2.5 Instant |
|---|---|---|
| LMArena Expert | 1266 | 1440 |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, Kimi K2.5 Instant: 40.2 (#50)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2.5 Instant |
|---|---|---|
| LMArena Vision | — | 1254 |
Multilingual Kimi K2.5 Instant leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Kimi K2.5 Instant: 52.0 (#94)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2.5 Instant |
|---|---|---|
| LMArena Non-English | 1273 | 1406 |
| LMArena Chinese | 1318 | 1449 |
| LMArena French | 1289 | 1403 |
| LMArena German | 1258 | 1413 |
| LMArena Korean | 1209 | 1378 |
| LMArena Russian | 1289 | 1404 |
| LMArena Spanish | 1248 | 1447 |
| LMArena Japanese | 1228 | — |
Instruction Following Kimi K2.5 Instant leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Kimi K2.5 Instant: 75.3 (#65)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2.5 Instant |
|---|---|---|
| LMArena Instruction Following | 1280 | 1430 |
Long Context Kimi K2.5 Instant leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Kimi K2.5 Instant: 43.9 (#83)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2.5 Instant |
|---|---|---|
| LMArena Longer Query | 1301 | 1435 |
Writing & Preference Kimi K2.5 Instant leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Kimi K2.5 Instant: 60.6 (#95)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2.5 Instant |
|---|---|---|
| LMArena Text | 1294 | 1420 |
| LMArena Creative Writing | 1285 | 1381 |
| LMArena Multi-Turn | 1297 | 1427 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Kimi K2.5 Instant?
Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Kimi K2.5 Instant better for coding?
Kimi K2.5 Instant scores higher on coding benchmarks: 42.6 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Kimi K2.5 Instant share?
16 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Kimi K2.5 Instant has 18.