Model comparison
DeepSeek-R1 vs Kimi K2.6
Kimi K2.6 is the stronger model overall, scoring 47.7 to 42.3 on the Noometry Index. DeepSeek-R1 costs 1.9× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
DeepSeekSummary
- They share 26 benchmarks with published results for both. DeepSeek-R1 scores higher in 2 categories and Kimi K2.6 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.6 leads 40.5 to 18.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.4% for DeepSeek-R1 and 96.1% for Kimi K2.6.
- DeepSeek-R1 is cheaper at $0.50 / $2.15 per million input/output tokens, against $0.95 / $4 for Kimi K2.6.
- Kimi K2.6 accepts more context: 262K tokens versus 164K.
- Kimi K2.6 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-R1 | Kimi K2.6 | |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Noometry Index | 42.3 | 47.7 |
| Released | 2025-01-20 | 2026-04-20 |
| Weights | Proprietary | Open |
| Context window | 164K | 262K |
| Max output | 64K | 262K |
| Input $ / M tokens | $0.50 | $0.95 |
| Output $ / M tokens | $2.15 | $4 |
| Results tracked | 52 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
DeepSeek-R1: 46.3 (#68), Kimi K2.6: 50.7 (#43)
| Benchmark | DeepSeek-R1 | Kimi K2.6 |
|---|---|---|
| SciCode | 35.7% | 53.5% |
| WeirdML | 41.6% | 55.9% |
| LMArena Coding | 1427 | 1488 |
| ALE-Bench | 804.12 | 1,093 |
| SWE-bench Verified | — | 76.7% |
| Aider Polyglot | 71.4% | — |
| LMArena WebDev | — | 1509 |
| LiveBench Coding | 66.7% | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use DeepSeek-R1 leads
DeepSeek-R1: 30.7 (#75), Kimi K2.6: 21.9 (#137)
| Benchmark | DeepSeek-R1 | Kimi K2.6 |
|---|---|---|
| OSWorld 2.0 | — | 4.6% |
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| METR Time Horizons | 53.8% | — |
| Vending-Bench 2 | — | 6,205 |
Reasoning Kimi K2.6 leads
DeepSeek-R1: 18.6 (#278), Kimi K2.6: 40.5 (#55)
| Benchmark | DeepSeek-R1 | Kimi K2.6 |
|---|---|---|
| CritPt | 1.1% | 8% |
| LMArena Hard Prompts | 1416 | 1470 |
| Epoch Capabilities Index | 141.29 | 151.05 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| Kagi LLM Benchmark | 69.4% | — |
| NYT Connections (extended) | — | 87.2% |
| ARC-AGI-1 | 21.2% | — |
| Chess Puzzles | — | 26% |
| EBR-Bench | — | 2.4% |
| LiveBench Reasoning | 83.2% | — |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 90.9% |
| LiveBench Data Analysis | 69.8% | — |
| LMCA | — | 37.3% |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math Kimi K2.6 leads
DeepSeek-R1: 43.8 (#79), Kimi K2.6: 57.0 (#41)
| Benchmark | DeepSeek-R1 | Kimi K2.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 96.1% |
| LMArena Math | 1400 | 1475 |
| FrontierMath (Tiers 1-3) | — | 57.2% |
| FrontierMath Tier 4 | — | 25.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
| ProofBench | — | 16% |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Kimi K2.6 leads
DeepSeek-R1: 44.5 (#87), Kimi K2.6: 54.0 (#54)
| Benchmark | DeepSeek-R1 | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 76.3% | 90.8% |
| Vectara Hallucination Rate | 11.3% | 10.8% |
| LMArena Expert | 1394 | 1491 |
| SimpleQA Verified | — | 34.9% |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| GPQA (HELM) | 66.6% | — |
Multimodal Not comparable
DeepSeek-R1: —, Kimi K2.6: 31.6 (#103)
| Benchmark | DeepSeek-R1 | Kimi K2.6 |
|---|---|---|
| LMArena Vision | — | 1283 |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Kimi K2.6 leads
DeepSeek-R1: 52.4 (#85), Kimi K2.6: 54.9 (#37)
| Benchmark | DeepSeek-R1 | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1412 | 1446 |
| LMArena Chinese | 1442 | 1521 |
| LMArena French | 1417 | 1471 |
| LMArena German | 1404 | 1450 |
| LMArena Japanese | 1391 | 1443 |
| LMArena Korean | 1360 | 1427 |
| LMArena Russian | 1423 | 1446 |
| LMArena Spanish | 1411 | 1464 |
Instruction Following Kimi K2.6 leads
DeepSeek-R1: 72.0 (#143), Kimi K2.6: 76.3 (#43)
| Benchmark | DeepSeek-R1 | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1382 | 1451 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
Long Context Too close to call
DeepSeek-R1: 45.4 (#36), Kimi K2.6: 44.9 (#52)
| Benchmark | DeepSeek-R1 | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1391 | 1468 |
| Fiction.LiveBench | 75% | — |
Writing & Preference Kimi K2.6 leads
DeepSeek-R1: 61.4 (#88), Kimi K2.6: 68.5 (#26)
| Benchmark | DeepSeek-R1 | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1428 | 1455 |
| LMArena Creative Writing | 1405 | 1434 |
| EQ-Bench Creative Writing | 1500 | 1725 |
| LMArena Multi-Turn | 1405 | 1453 |
| Short-Story Creative Writing | 83% | — |
| WildBench | 82.8% | — |
| EQ-Bench 4 | — | 1202 |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than Kimi K2.6?
Kimi K2.6 is the stronger model overall, scoring 47.7 to 42.3 on the Noometry Index. DeepSeek-R1 costs 1.9× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-R1 or Kimi K2.6?
DeepSeek-R1 is cheaper. It lists at $0.50 per million input tokens and $2.15 per million output tokens; Kimi K2.6 lists at $0.95 and $4.
Is DeepSeek-R1 or Kimi K2.6 better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 46.3 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.6 does, with 262K tokens against 164K.
How many benchmarks do DeepSeek-R1 and Kimi K2.6 share?
26 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Kimi K2.6 has 51.