Model comparison
DeepSeek-V3.2-Exp vs Kimi K2.5 Instant
DeepSeek-V3.2-Exp and Kimi K2.5 Instant score almost the same on the Noometry Index (44.3 vs 43.6), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 6 categories and Kimi K2.5 Instant 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 40.2.
Side by side
| DeepSeek-V3.2-Exp | Kimi K2.5 Instant | |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Noometry Index | 44.3 | 43.6 |
| Released | 2025-09-29 | — |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.26 | — |
| Output $ / M tokens | $0.38 | — |
| Results tracked | 49 | 18 |
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 K2.5 Instant: 42.6 (#97)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2.5 Instant |
|---|---|---|
| LMArena WebDev | 1362 | 1404 |
| LMArena Coding | 1454 | 1484 |
| 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: 32.7 (#59), Kimi K2.5 Instant: —
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2.5 Instant |
|---|---|---|
| Terminal-Bench | 39.6% | — |
| APEX-Agents | 21.3% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| TheAgentCompany | 42.9% | — |
| Vending-Bench 2 | 1,034 | — |
Reasoning Kimi K2.5 Instant leads
DeepSeek-V3.2-Exp: 22.1 (#208), Kimi K2.5 Instant: 29.7 (#90)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2.5 Instant |
|---|---|---|
| LMArena Hard Prompts | 1434 | 1443 |
| ARC-AGI-2 | 4% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 36.7% | — |
| ARC-AGI-1 | 57% | — |
| CritPt | 2.9% | — |
| Chess Puzzles | 14% | — |
| Thematic Generalization | 65% | — |
| DTBench | 87.7% | — |
| LMCA | 29.1% | — |
| Epoch Capabilities Index | 146.27 | — |
Math DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 41.7 (#87), Kimi K2.5 Instant: 39.4 (#105)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2.5 Instant |
|---|---|---|
| LMArena Math | 1435 | 1442 |
| MathArena Final-Answer Competitions | 57.7% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| ProofBench | 8% | — |
| FrontierMath (Feb 2025 set) | 22.1% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 51.7 (#66), Kimi K2.5 Instant: 40.2 (#123)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2.5 Instant |
|---|---|---|
| LMArena Expert | 1436 | 1440 |
| GPQA Diamond | 83.4% | — |
| Vectara Hallucination Rate | 5.3% | — |
Multimodal Not comparable
DeepSeek-V3.2-Exp: —, Kimi K2.5 Instant: 40.2 (#50)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2.5 Instant |
|---|---|---|
| LMArena Vision | — | 1254 |
Multilingual Too close to call
DeepSeek-V3.2-Exp: 52.2 (#90), Kimi K2.5 Instant: 52.0 (#94)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2.5 Instant |
|---|---|---|
| LMArena Non-English | 1409 | 1406 |
| LMArena Chinese | 1461 | 1449 |
| LMArena French | 1433 | 1403 |
| LMArena German | 1440 | 1413 |
| LMArena Korean | 1371 | 1378 |
| LMArena Russian | 1424 | 1404 |
| LMArena Spanish | 1440 | 1447 |
| LMArena Japanese | 1374 | — |
Instruction Following Too close to call
DeepSeek-V3.2-Exp: 74.5 (#93), Kimi K2.5 Instant: 75.3 (#65)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2.5 Instant |
|---|---|---|
| LMArena Instruction Following | 1413 | 1430 |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#16), Kimi K2.5 Instant: 43.9 (#83)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2.5 Instant |
|---|---|---|
| LMArena Longer Query | 1428 | 1435 |
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
Writing & Preference DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 62.4 (#77), Kimi K2.5 Instant: 60.6 (#95)
| Benchmark | DeepSeek-V3.2-Exp | Kimi K2.5 Instant |
|---|---|---|
| LMArena Text | 1425 | 1420 |
| LMArena Creative Writing | 1403 | 1381 |
| LMArena Multi-Turn | 1427 | 1427 |
| EQ-Bench Creative Writing | 1515 | — |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than Kimi K2.5 Instant?
DeepSeek-V3.2-Exp and Kimi K2.5 Instant score almost the same on the Noometry Index (44.3 vs 43.6), so choose on price, context window or the category you care about most.
Is DeepSeek-V3.2-Exp or Kimi K2.5 Instant better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 42.6 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.2-Exp and Kimi K2.5 Instant share?
17 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and Kimi K2.5 Instant has 18.