Model comparison
DeepSeek-V3.2-Exp vs Kimi K2 (Jul 2025)
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 41.2 on the Noometry Index.
Last verified . 30 shared benchmarks.
DeepSeekSummary
- They share 30 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 7 categories and Kimi K2 (Jul 2025) in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.7 to 37.3.
- The biggest single-benchmark swing is Fiction.LiveBench: 83.3% for DeepSeek-V3.2-Exp and 66.7% for Kimi K2 (Jul 2025).
- DeepSeek-V3.2-Exp is cheaper at $0.26 / $0.38 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-V3.2-Exp | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Noometry Index | 44.3 | 41.2 |
| Released | 2025-09-29 | 2025-07-12 |
| Weights | Open | Open |
| Context window | 164K | 262K |
| Max output | 66K | 262K |
| Input $ / M tokens | $0.26 | $0.57 |
| Output $ / M tokens | $0.38 | $2.30 |
| Results tracked | 49 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 46.5 (#65), Kimi K2 (Jul 2025): 42.4 (#102)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2 (Jul 2025) |
|---|---|---|
| SWE-bench Verified (bash only) | 70% | 63.4% |
| Aider Polyglot | 74.2% | 59.1% |
| WeirdML | 39.5% | 42.8% |
| LMArena Coding | 1454 | 1399 |
| LMArena WebDev | 1362 | — |
| SWE-bench Multilingual | 59% | — |
| SciCode | 38.9% | — |
| GSO | — | 4.9% |
| ALE-Bench | — | 597.5 |
Agentic & Tool Use Too close to call
DeepSeek-V3.2-Exp: 32.7 (#59), Kimi K2 (Jul 2025): 32.4 (#64)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | 39.6% | 35.7% |
| Berkeley Function Calling Leaderboard | 56.7% | 59.1% |
| APEX-Agents | 21.3% | — |
| TheAgentCompany | 42.9% | — |
| METR Time Horizons | — | 59.2% |
| Vending-Bench 2 | 1,034 | — |
Reasoning Kimi K2 (Jul 2025) leads
DeepSeek-V3.2-Exp: 22.1 (#208), Kimi K2 (Jul 2025): 23.3 (#179)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2 (Jul 2025) |
|---|---|---|
| Kagi LLM Benchmark | 52.2% | 64.4% |
| LMArena Hard Prompts | 1434 | 1384 |
| Epoch Capabilities Index | 146.27 | 146.01 |
| ARC-AGI-2 | 4% | — |
| SimpleBench | — | 26.3% |
| NYT Connections (extended) | 36.7% | — |
| ARC-AGI-1 | 57% | — |
| CritPt | 2.9% | — |
| Chess Puzzles | 14% | — |
| Thematic Generalization | 65% | — |
| DTBench | 87.7% | — |
| LMCA | 29.1% | — |
| ForecastBench | — | 60.2 |
Math Too close to call
DeepSeek-V3.2-Exp: 41.7 (#87), Kimi K2 (Jul 2025): 42.7 (#83)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Math | 1435 | 1397 |
| FrontierMath (Feb 2025 set) | 22.1% | 21.4% |
| FrontierMath Tier 4 (v1) | 2.1% | 0% |
| MathArena Final-Answer Competitions | 57.7% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| ProofBench | 8% | — |
| Omni-MATH | — | 65.4% |
Knowledge DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 51.7 (#66), Kimi K2 (Jul 2025): 37.3 (#157)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2 (Jul 2025) |
|---|---|---|
| Vectara Hallucination Rate | 5.3% | 17.9% |
| LMArena Expert | 1436 | 1365 |
| GPQA Diamond | 83.4% | — |
| MMLU-Pro | — | 81.9% |
| Confabulations | — | 20.4% |
| GPQA (HELM) | — | 65.3% |
Multilingual DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 52.2 (#90), Kimi K2 (Jul 2025): 49.6 (#130)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1409 | 1372 |
| LMArena Chinese | 1461 | 1415 |
| LMArena French | 1433 | 1379 |
| LMArena German | 1440 | 1387 |
| LMArena Japanese | 1374 | 1349 |
| LMArena Korean | 1371 | 1325 |
| LMArena Russian | 1424 | 1385 |
| LMArena Spanish | 1440 | 1386 |
Instruction Following DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 74.5 (#93), Kimi K2 (Jul 2025): 71.1 (#156)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Instruction Following | 1413 | 1348 |
| IFEval | — | 85% |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#16), Kimi K2 (Jul 2025): 41.2 (#145)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2 (Jul 2025) |
|---|---|---|
| Fiction.LiveBench | 83.3% | 66.7% |
| CL-bench | 13.2% | 17.6% |
| LMArena Longer Query | 1428 | 1353 |
| CL-bench Life | 9.5% | — |
Writing & Preference Too close to call
DeepSeek-V3.2-Exp: 62.4 (#77), Kimi K2 (Jul 2025): 62.3 (#78)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1425 | 1380 |
| LMArena Creative Writing | 1403 | 1350 |
| EQ-Bench Creative Writing | 1515 | 1666 |
| LMArena Multi-Turn | 1427 | 1371 |
| Short-Story Creative Writing | — | 85.6% |
| WildBench | — | 86.2% |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than Kimi K2 (Jul 2025)?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 41.2 on the Noometry Index.
Which is cheaper, DeepSeek-V3.2-Exp or Kimi K2 (Jul 2025)?
DeepSeek-V3.2-Exp is cheaper. It lists at $0.26 per million input tokens and $0.38 per million output tokens; Kimi K2 (Jul 2025) lists at $0.57 and $2.30.
Is DeepSeek-V3.2-Exp or Kimi K2 (Jul 2025) better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 42.4 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-V3.2-Exp and Kimi K2 (Jul 2025) share?
30 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and Kimi K2 (Jul 2025) has 42.