Model comparison
Gemini 3 Deep Think vs Kimi K2.5 Instant
Kimi K2.5 Instant has enough public results to be ranked (#92); Gemini 3 Deep Think does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
GoogleSummary
- The widest gap is in reasoning, where Gemini 3 Deep Think leads 70.8 to 28.5.
- Kimi K2.5 Instant has downloadable open weights; the other is API-only.
Side by side
| Gemini 3 Deep Think | Kimi K2.5 Instant | |
|---|---|---|
| Provider | Moonshot AI | |
| Noometry Index | 58.5 | 42.9 |
| Released | 2026-02-12 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 3 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemini 3 Deep Think: —, Kimi K2.5 Instant: 42.3 (#95)
| Benchmark | Gemini 3 Deep Think | Kimi K2.5 Instant |
|---|---|---|
| LMArena WebDev | — | 1404 |
| LMArena Coding | — | 1483 |
Reasoning Gemini 3 Deep Think leads
Gemini 3 Deep Think: 70.8 (#11), Kimi K2.5 Instant: 28.5 (#88)
| Benchmark | Gemini 3 Deep Think | Kimi K2.5 Instant |
|---|---|---|
| ARC-AGI-2 | 84.6% | — |
| ARC-AGI-1 | 96% | — |
| CritPt | 25.7% | — |
| LMArena Hard Prompts | — | 1443 |
Math Not comparable
Gemini 3 Deep Think: —, Kimi K2.5 Instant: 36.6 (#105)
| Benchmark | Gemini 3 Deep Think | Kimi K2.5 Instant |
|---|---|---|
| LMArena Math | — | 1443 |
Knowledge Not comparable
Gemini 3 Deep Think: —, Kimi K2.5 Instant: 39.5 (#121)
| Benchmark | Gemini 3 Deep Think | Kimi K2.5 Instant |
|---|---|---|
| LMArena Expert | — | 1438 |
Multimodal Not comparable
Gemini 3 Deep Think: —, Kimi K2.5 Instant: 39.5 (#47)
| Benchmark | Gemini 3 Deep Think | Kimi K2.5 Instant |
|---|---|---|
| LMArena Vision | — | 1254 |
Multilingual Not comparable
Gemini 3 Deep Think: —, Kimi K2.5 Instant: 52.2 (#89)
| Benchmark | Gemini 3 Deep Think | Kimi K2.5 Instant |
|---|---|---|
| LMArena Non-English | — | 1406 |
| LMArena Chinese | — | 1450 |
| LMArena French | — | 1403 |
| LMArena German | — | 1413 |
| LMArena Korean | — | 1378 |
| LMArena Russian | — | 1404 |
| LMArena Spanish | — | 1448 |
Instruction Following Not comparable
Gemini 3 Deep Think: —, Kimi K2.5 Instant: 75.5 (#61)
| Benchmark | Gemini 3 Deep Think | Kimi K2.5 Instant |
|---|---|---|
| LMArena Instruction Following | — | 1430 |
Long Context Not comparable
Gemini 3 Deep Think: —, Kimi K2.5 Instant: 43.8 (#82)
| Benchmark | Gemini 3 Deep Think | Kimi K2.5 Instant |
|---|---|---|
| LMArena Longer Query | — | 1435 |
Writing & Preference Not comparable
Gemini 3 Deep Think: —, Kimi K2.5 Instant: 60.8 (#91)
| Benchmark | Gemini 3 Deep Think | Kimi K2.5 Instant |
|---|---|---|
| LMArena Text | — | 1420 |
| LMArena Creative Writing | — | 1379 |
| LMArena Multi-Turn | — | 1427 |
Frequently asked questions
Is Gemini 3 Deep Think better than Kimi K2.5 Instant?
Kimi K2.5 Instant has enough public results to be ranked (#92); Gemini 3 Deep Think does not yet, so treat this comparison as directional.
How many benchmarks do Gemini 3 Deep Think and Kimi K2.5 Instant share?
0 benchmarks have published results for both models. Gemini 3 Deep Think has 3 scored results on Noometry and Kimi K2.5 Instant has 18.