Model comparison
DeepSeek-V2.5 (Sep 2024) vs Kimi K2.6
Kimi K2.6 is the stronger model overall, scoring 47.5 to 37.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and Kimi K2.6 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.6 leads 56.8 to 33.3.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Kimi K2.6 | |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Noometry Index | 37.0 | 47.5 |
| Released | 2024-09-06 | 2026-04-20 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.95 |
| Output $ / M tokens | — | $4 |
| Results tracked | 22 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
DeepSeek-V2.5 (Sep 2024): 31.3 (#274), Kimi K2.6: 50.5 (#41)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2.6 |
|---|---|---|
| LMArena Coding | 1310 | 1488 |
| SWE-bench Verified | — | 76.7% |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1509 |
| SciCode | — | 53.5% |
| WeirdML | — | 55.9% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 1,093 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, Kimi K2.6: 21.8 (#128)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2.6 |
|---|---|---|
| OSWorld 2.0 | — | 4.6% |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| Vending-Bench 2 | — | 6,205 |
Reasoning Kimi K2.6 leads
DeepSeek-V2.5 (Sep 2024): 24.5 (#145), Kimi K2.6: 39.6 (#51)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2.6 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1470 |
| NYT Connections (extended) | — | 87.2% |
| CritPt | — | 8% |
| Chess Puzzles | — | 26% |
| EBR-Bench | — | 2.4% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 90.9% |
| LMCA | — | 37.3% |
| Epoch Capabilities Index | — | 151.03 |
Math Kimi K2.6 leads
DeepSeek-V2.5 (Sep 2024): 33.3 (#177), Kimi K2.6: 56.8 (#34)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2.6 |
|---|---|---|
| LMArena Math | 1289 | 1475 |
| FrontierMath (Tiers 1-3) | — | 57.2% |
| FrontierMath Tier 4 | — | 25.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
| OTIS Mock AIME 2024-2025 | — | 96.1% |
| ProofBench | — | 16% |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Kimi K2.6 leads
DeepSeek-V2.5 (Sep 2024): 34.2 (#190), Kimi K2.6: 53.9 (#48)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2.6 |
|---|---|---|
| LMArena Expert | 1266 | 1491 |
| GPQA Diamond | — | 90.8% |
| SimpleQA Verified | — | 34.9% |
| Vectara Hallucination Rate | — | 10.8% |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, Kimi K2.6: 31.8 (#95)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2.6 |
|---|---|---|
| LMArena Vision | — | 1282 |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Kimi K2.6 leads
DeepSeek-V2.5 (Sep 2024): 42.7 (#188), Kimi K2.6: 55.1 (#35)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1273 | 1446 |
| LMArena Chinese | 1317 | 1521 |
| LMArena French | 1288 | 1471 |
| LMArena German | 1258 | 1449 |
| LMArena Japanese | 1228 | 1442 |
| LMArena Korean | 1209 | 1428 |
| LMArena Russian | 1289 | 1446 |
| LMArena Spanish | 1248 | 1463 |
Instruction Following Kimi K2.6 leads
DeepSeek-V2.5 (Sep 2024): 67.7 (#189), Kimi K2.6: 76.5 (#40)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1451 |
Long Context Kimi K2.6 leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#169), Kimi K2.6: 44.9 (#50)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1301 | 1468 |
Writing & Preference Kimi K2.6 leads
DeepSeek-V2.5 (Sep 2024): 50.0 (#182), Kimi K2.6: 68.7 (#25)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1294 | 1455 |
| LMArena Creative Writing | 1285 | 1434 |
| LMArena Multi-Turn | 1297 | 1453 |
| EQ-Bench Creative Writing | — | 1725 |
| EQ-Bench 4 | — | 1202 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Kimi K2.6?
Kimi K2.6 is the stronger model overall, scoring 47.5 to 37.0 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Kimi K2.6 better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.5 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Kimi K2.6 share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Kimi K2.6 has 51.