Model comparison
Gemini 2.5 Flash vs Kimi K2 Thinking Turbo
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 39.0 on the Noometry Index.
Last verified . 18 shared benchmarks.
GoogleSummary
- They share 18 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 3 categories and Kimi K2 Thinking Turbo in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2 Thinking Turbo leads 50.9 to 36.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 73.1% for Gemini 2.5 Flash and 83.1% for Kimi K2 Thinking Turbo.
- Kimi K2 Thinking Turbo has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash | Kimi K2 Thinking Turbo | |
|---|---|---|
| Provider | Moonshot AI | |
| Noometry Index | 39.0 | 45.4 |
| Released | 2025-04-17 | 2025-11-06 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 54 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 Thinking Turbo leads
Gemini 2.5 Flash: 35.5 (#210), Kimi K2 Thinking Turbo: 38.1 (#166)
| Benchmark | Gemini 2.5 Flash | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Coding | 1424 | 1454 |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1322 |
| WeirdML | 41.9% | — |
| ALE-Bench | 661.88 | — |
Agentic & Tool Use Not comparable
Gemini 2.5 Flash: 30.6 (#67), Kimi K2 Thinking Turbo: —
| Benchmark | Gemini 2.5 Flash | Kimi K2 Thinking Turbo |
|---|---|---|
| Terminal-Bench | 17.1% | — |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |
Reasoning Kimi K2 Thinking Turbo leads
Gemini 2.5 Flash: 18.2 (#271), Kimi K2 Thinking Turbo: 31.4 (#72)
| Benchmark | Gemini 2.5 Flash | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Hard Prompts | 1422 | 1428 |
| ARC-AGI-2 | 2.5% | — |
| SimpleBench | 41.2% | — |
| Kagi LLM Benchmark | 56.8% | — |
| ARC-AGI-1 | 33.3% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | — | 20% |
| EnigmaEval | 2.7% | — |
| DTBench | 76.5% | — |
| LMCA | 27.5% | — |
| Epoch Capabilities Index | 143.04 | — |
| ForecastBench | 60.6 | — |
Math Kimi K2 Thinking Turbo leads
Gemini 2.5 Flash: 38.1 (#87), Kimi K2 Thinking Turbo: 45.5 (#62)
| Benchmark | Gemini 2.5 Flash | Kimi K2 Thinking Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 83.1% |
| LMArena Math | 1415 | 1429 |
| Omni-MATH | 38.5% | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Kimi K2 Thinking Turbo leads
Gemini 2.5 Flash: 36.1 (#162), Kimi K2 Thinking Turbo: 50.9 (#64)
| Benchmark | Gemini 2.5 Flash | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Expert | 1426 | 1439 |
| GPQA Diamond | — | 84.2% |
| Humanity's Last Exam | 12.1% | — |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| Vectara Hallucination Rate | 7.8% | — |
| GPQA (HELM) | 39% | — |
Multimodal Not comparable
Gemini 2.5 Flash: 41.2 (#31), Kimi K2 Thinking Turbo: —
| Benchmark | Gemini 2.5 Flash | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Vision | 1254 | — |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Too close to call
Gemini 2.5 Flash: 52.5 (#83), Kimi K2 Thinking Turbo: 51.6 (#104)
| Benchmark | Gemini 2.5 Flash | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Non-English | 1410 | 1398 |
| LMArena Chinese | 1450 | 1457 |
| LMArena French | 1433 | 1425 |
| LMArena German | 1419 | 1390 |
| LMArena Japanese | 1403 | 1356 |
| LMArena Korean | 1385 | 1329 |
| LMArena Russian | 1415 | 1390 |
| LMArena Spanish | 1421 | 1407 |
Instruction Following Gemini 2.5 Flash leads
Gemini 2.5 Flash: 75.9 (#50), Kimi K2 Thinking Turbo: 74.2 (#103)
| Benchmark | Gemini 2.5 Flash | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Instruction Following | 1405 | 1403 |
| IFEval | 89.8% | — |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#16), Kimi K2 Thinking Turbo: 43.2 (#99)
| Benchmark | Gemini 2.5 Flash | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Longer Query | 1419 | 1415 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference Kimi K2 Thinking Turbo leads
Gemini 2.5 Flash: 54.0 (#153), Kimi K2 Thinking Turbo: 60.2 (#99)
| Benchmark | Gemini 2.5 Flash | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Text | 1417 | 1415 |
| LMArena Creative Writing | 1400 | 1373 |
| LMArena Multi-Turn | 1408 | 1414 |
| Short-Story Creative Writing | 76.5% | — |
| EQ-Bench Creative Writing | 1137 | — |
| WildBench | 81.7% | — |
Frequently asked questions
Is Gemini 2.5 Flash better than Kimi K2 Thinking Turbo?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 39.0 on the Noometry Index.
Is Gemini 2.5 Flash or Kimi K2 Thinking Turbo better for coding?
Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.1 versus 35.5 in the Noometry coding category.
How many benchmarks do Gemini 2.5 Flash and Kimi K2 Thinking Turbo share?
18 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Kimi K2 Thinking Turbo has 21.