Model comparison
DeepSeek-V3.2-Exp vs Kimi K2 Thinking Turbo
DeepSeek-V3.2-Exp and Kimi K2 Thinking Turbo score almost the same on the Noometry Index (44.9 vs 45.4), so choose on price, context window or the category you care about most.
Last verified . 21 shared benchmarks.
DeepSeekSummary
- They share 21 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 6 categories and Kimi K2 Thinking Turbo in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2 Thinking Turbo leads 31.4 to 22.0.
- The biggest single-benchmark swing is Chess Puzzles: 14% for DeepSeek-V3.2-Exp and 20% for Kimi K2 Thinking Turbo.
Side by side
| DeepSeek-V3.2-Exp | Kimi K2 Thinking Turbo | |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Noometry Index | 44.9 | 45.4 |
| Released | 2025-09-29 | 2025-11-06 |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.26 | — |
| Output $ / M tokens | $0.38 | — |
| Results tracked | 48 | 21 |
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: 46.4 (#61), Kimi K2 Thinking Turbo: 38.1 (#166)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena WebDev | 1362 | 1322 |
| LMArena Coding | 1454 | 1454 |
| SWE-bench Verified (bash only) | 70% | — |
| Aider Polyglot | 74.2% | — |
| SWE-bench Multilingual | 59% | — |
| SciCode | 38.9% | — |
| WeirdML | 39.5% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.2-Exp: 37.9 (#31), Kimi K2 Thinking Turbo: —
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2 Thinking Turbo |
|---|---|---|
| Terminal-Bench | 39.6% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| TheAgentCompany | 42.9% | — |
| Vending-Bench 2 | 1,034 | — |
Reasoning Kimi K2 Thinking Turbo leads
DeepSeek-V3.2-Exp: 22.0 (#185), Kimi K2 Thinking Turbo: 31.4 (#72)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2 Thinking Turbo |
|---|---|---|
| Chess Puzzles | 14% | 20% |
| LMArena Hard Prompts | 1433 | 1428 |
| ARC-AGI-2 | 4% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 36.7% | — |
| ARC-AGI-1 | 57% | — |
| CritPt | 2.9% | — |
| Thematic Generalization | 65% | — |
| DTBench | 87.7% | — |
| LMCA | 29.1% | — |
| Epoch Capabilities Index | 146.28 | — |
Math Kimi K2 Thinking Turbo leads
DeepSeek-V3.2-Exp: 40.8 (#75), Kimi K2 Thinking Turbo: 45.5 (#62)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2 Thinking Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 87.8% | 83.1% |
| LMArena Math | 1435 | 1429 |
| MathArena Final-Answer Competitions | 57.7% | — |
| ProofBench | 8% | — |
| FrontierMath (Feb 2025 set) | 22.1% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Too close to call
DeepSeek-V3.2-Exp: 51.6 (#61), Kimi K2 Thinking Turbo: 50.9 (#64)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2 Thinking Turbo |
|---|---|---|
| GPQA Diamond | 83.4% | 84.2% |
| LMArena Expert | 1436 | 1439 |
| Vectara Hallucination Rate | 5.3% | — |
Multilingual Too close to call
DeepSeek-V3.2-Exp: 52.4 (#85), Kimi K2 Thinking Turbo: 51.6 (#104)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Non-English | 1409 | 1398 |
| LMArena Chinese | 1461 | 1457 |
| LMArena French | 1435 | 1425 |
| LMArena German | 1440 | 1390 |
| LMArena Japanese | 1377 | 1356 |
| LMArena Korean | 1372 | 1329 |
| LMArena Russian | 1423 | 1390 |
| LMArena Spanish | 1441 | 1407 |
Instruction Following Too close to call
DeepSeek-V3.2-Exp: 74.7 (#89), Kimi K2 Thinking Turbo: 74.2 (#103)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Instruction Following | 1413 | 1403 |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#15), Kimi K2 Thinking Turbo: 43.2 (#99)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Longer Query | 1428 | 1415 |
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
Writing & Preference DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 62.5 (#73), Kimi K2 Thinking Turbo: 60.2 (#99)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Text | 1425 | 1415 |
| LMArena Creative Writing | 1403 | 1373 |
| LMArena Multi-Turn | 1427 | 1414 |
| EQ-Bench Creative Writing | 1515 | — |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than Kimi K2 Thinking Turbo?
DeepSeek-V3.2-Exp and Kimi K2 Thinking Turbo score almost the same on the Noometry Index (44.9 vs 45.4), so choose on price, context window or the category you care about most.
Is DeepSeek-V3.2-Exp or Kimi K2 Thinking Turbo better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.4 versus 38.1 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.2-Exp and Kimi K2 Thinking Turbo share?
21 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 48 scored results on Noometry and Kimi K2 Thinking Turbo has 21.