Model comparison
DeepSeek-V3.1 vs Kimi K2 (Jul 2025)
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 41.2 on the Noometry Index.
Last verified . 25 shared benchmarks.
DeepSeekSummary
- They share 25 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 4 categories and Kimi K2 (Jul 2025) in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.1 leads 43.7 to 37.3.
- The biggest single-benchmark swing is Fiction.LiveBench: 52.8% for DeepSeek-V3.1 and 66.7% for Kimi K2 (Jul 2025).
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $0.57 / $2.30 for Kimi K2 (Jul 2025).
- Kimi K2 (Jul 2025) accepts more context: 262K tokens versus 164K.
Side by side
| DeepSeek-V3.1 | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Noometry Index | 42.8 | 41.2 |
| Released | 2025-08-21 | 2025-07-12 |
| Weights | Open | Open |
| Context window | 164K | 262K |
| Max output | 8K | 262K |
| Input $ / M tokens | $0.25 | $0.57 |
| Output $ / M tokens | $0.95 | $2.30 |
| Results tracked | 27 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
DeepSeek-V3.1: 40.3 (#144), Kimi K2 (Jul 2025): 42.4 (#102)
| Benchmark | DeepSeek-V3.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| WeirdML | 38.4% | 42.8% |
| LMArena Coding | 1417 | 1399 |
| SWE-bench Verified (bash only) | — | 63.4% |
| Aider Polyglot | — | 59.1% |
| GSO | — | 4.9% |
| ALE-Bench | — | 597.5 |
Agentic & Tool Use Not comparable
DeepSeek-V3.1: —, Kimi K2 (Jul 2025): 32.4 (#64)
| Benchmark | DeepSeek-V3.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | — | 35.7% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| METR Time Horizons | — | 59.2% |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), Kimi K2 (Jul 2025): 23.3 (#179)
| Benchmark | DeepSeek-V3.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| SimpleBench | 40% | 26.3% |
| Kagi LLM Benchmark | 53.2% | 64.4% |
| LMArena Hard Prompts | 1417 | 1384 |
| Epoch Capabilities Index | 139.92 | 146.01 |
| ForecastBench | 58 | 60.2 |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
Math Kimi K2 (Jul 2025) leads
DeepSeek-V3.1: 38.9 (#122), Kimi K2 (Jul 2025): 42.7 (#83)
| Benchmark | DeepSeek-V3.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Math | 1420 | 1397 |
| Omni-MATH | — | 65.4% |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), Kimi K2 (Jul 2025): 37.3 (#157)
| Benchmark | DeepSeek-V3.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 17.9% |
| LMArena Expert | 1405 | 1365 |
| MMLU-Pro | — | 81.9% |
| Confabulations | — | 20.4% |
| GPQA (HELM) | — | 65.3% |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), Kimi K2 (Jul 2025): 49.6 (#130)
| Benchmark | DeepSeek-V3.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1400 | 1372 |
| LMArena Chinese | 1469 | 1415 |
| LMArena French | 1447 | 1379 |
| LMArena German | 1411 | 1387 |
| LMArena Japanese | 1378 | 1349 |
| LMArena Korean | 1337 | 1325 |
| LMArena Russian | 1405 | 1385 |
| LMArena Spanish | 1431 | 1386 |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 73.9 (#110), Kimi K2 (Jul 2025): 71.1 (#156)
| Benchmark | DeepSeek-V3.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Instruction Following | 1400 | 1348 |
| IFEval | — | 85% |
Long Context Kimi K2 (Jul 2025) leads
DeepSeek-V3.1: 36.3 (#232), Kimi K2 (Jul 2025): 41.2 (#145)
| Benchmark | DeepSeek-V3.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| Fiction.LiveBench | 52.8% | 66.7% |
| LMArena Longer Query | 1422 | 1353 |
| CL-bench | — | 17.6% |
Writing & Preference Kimi K2 (Jul 2025) leads
DeepSeek-V3.1: 60.3 (#98), Kimi K2 (Jul 2025): 62.3 (#78)
| Benchmark | DeepSeek-V3.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1420 | 1380 |
| LMArena Creative Writing | 1401 | 1350 |
| EQ-Bench Creative Writing | 1436 | 1666 |
| LMArena Multi-Turn | 1408 | 1371 |
| Short-Story Creative Writing | — | 85.6% |
| WildBench | — | 86.2% |
Frequently asked questions
Is DeepSeek-V3.1 better than Kimi K2 (Jul 2025)?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 41.2 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1 or Kimi K2 (Jul 2025)?
DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Kimi K2 (Jul 2025) lists at $0.57 and $2.30.
Is DeepSeek-V3.1 or Kimi K2 (Jul 2025) better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 40.3 in the Noometry coding category.
Which has the bigger context window?
Kimi K2 (Jul 2025) does, with 262K tokens against 164K.
How many benchmarks do DeepSeek-V3.1 and Kimi K2 (Jul 2025) share?
25 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Kimi K2 (Jul 2025) has 42.