Model comparison
Gemini 3.1 Pro Preview vs Kimi K2.5 Instant
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 42.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
GoogleSummary
- They share 18 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 8 categories and Kimi K2.5 Instant in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 28.5.
- Kimi K2.5 Instant has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.1 Pro Preview | Kimi K2.5 Instant | |
|---|---|---|
| Provider | Moonshot AI | |
| Noometry Index | 56.7 | 42.9 |
| Released | 2026-02-19 | — |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $12 | — |
| Results tracked | 71 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 3.1 Pro Preview: 42.7 (#88), Kimi K2.5 Instant: 42.3 (#95)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2.5 Instant |
|---|---|---|
| LMArena WebDev | 1446 | 1404 |
| LMArena Coding | 1483 | 1483 |
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| SciCode | 58.9% | — |
| GSO | 22.6% | — |
| WeirdML | 72.1% | — |
| MirrorCode | 8.9% | — |
| ALE-Bench | 1,161 | — |
| AlgoTune | 2.02 | — |
Agentic & Tool Use Not comparable
Gemini 3.1 Pro Preview: 37.7 (#33), Kimi K2.5 Instant: —
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2.5 Instant |
|---|---|---|
| Terminal-Bench | 80.2% | — |
| APEX-Agents | 35.3% | — |
| τ²-bench Banking | 26% | — |
| DeepResearch Bench | 47.8% | — |
| PostTrainBench | 22% | — |
| BALROG | 57% | — |
| ExploitBench | 26.1% | — |
| GBAEval | 0.8% | — |
| GDP.pdf | 17% | — |
| LMArena Search | 1211 | — |
| METR Time Horizons | 77% | — |
| Vending-Bench 2 | 3,774 | — |
Reasoning Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 71.7 (#9), Kimi K2.5 Instant: 28.5 (#88)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2.5 Instant |
|---|---|---|
| LMArena Hard Prompts | 1484 | 1443 |
| ARC-AGI-2 | 77.1% | — |
| SimpleBench | 79.6% | — |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | 98% | — |
| CritPt | 17.7% | — |
| Chess Puzzles | 55% | — |
| EnigmaEval | 36.8% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.1% | — |
| LMCA | 53.8% | — |
| Epoch Capabilities Index | 154.92 | — |
| ForecastBench | 59 | — |
Math Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 61.8 (#28), Kimi K2.5 Instant: 36.6 (#105)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2.5 Instant |
|---|---|---|
| LMArena Math | 1485 | 1443 |
| FrontierMath (Tiers 1-3) | 59.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| ProofBench | 26% | — |
| FrontierMath (Feb 2025 set) | 36.9% | — |
| FrontierMath Tier 4 (v1) | 16.7% | — |
Knowledge Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 71.8 (#3), Kimi K2.5 Instant: 39.5 (#121)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2.5 Instant |
|---|---|---|
| LMArena Expert | 1484 | 1438 |
| GPQA Diamond | 94.4% | — |
| Humanity's Last Exam | 46.4% | — |
| SimpleQA Verified | 73.5% | — |
| Vectara Hallucination Rate | 10.4% | — |
Multimodal Kimi K2.5 Instant leads
Gemini 3.1 Pro Preview: 38.1 (#60), Kimi K2.5 Instant: 39.5 (#47)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2.5 Instant |
|---|---|---|
| LMArena Vision | 1296 | 1254 |
| Blueprint-Bench 2 | 26.5% | — |
| Furniture Assembly | 26.7% | — |
| LMArena Document | 1444 | — |
Multilingual Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 57.1 (#11), Kimi K2.5 Instant: 52.2 (#89)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2.5 Instant |
|---|---|---|
| LMArena Non-English | 1475 | 1406 |
| LMArena Chinese | 1528 | 1450 |
| LMArena French | 1488 | 1403 |
| LMArena German | 1491 | 1413 |
| LMArena Korean | 1458 | 1378 |
| LMArena Russian | 1496 | 1404 |
| LMArena Spanish | 1480 | 1448 |
| LMArena Japanese | 1494 | — |
Instruction Following Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 77.1 (#31), Kimi K2.5 Instant: 75.5 (#61)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2.5 Instant |
|---|---|---|
| LMArena Instruction Following | 1465 | 1430 |
Long Context Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 47.3 (#17), Kimi K2.5 Instant: 43.8 (#82)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2.5 Instant |
|---|---|---|
| LMArena Longer Query | 1482 | 1435 |
| CL-bench | 20.8% | — |
| CL-bench Life | 16.9% | — |
Writing & Preference Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 66.3 (#36), Kimi K2.5 Instant: 60.8 (#91)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2.5 Instant |
|---|---|---|
| LMArena Text | 1480 | 1420 |
| LMArena Creative Writing | 1482 | 1379 |
| LMArena Multi-Turn | 1486 | 1427 |
| EQ-Bench Creative Writing | 1491 | — |
| EQ-Bench 4 | 1142 | — |
Frequently asked questions
Is Gemini 3.1 Pro Preview better than Kimi K2.5 Instant?
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 42.9 on the Noometry Index.
Is Gemini 3.1 Pro Preview or Kimi K2.5 Instant better for coding?
They score almost the same on coding (42.7 vs 42.3); test both on your own repository before choosing.
How many benchmarks do Gemini 3.1 Pro Preview and Kimi K2.5 Instant share?
18 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Kimi K2.5 Instant has 18.