Model comparison
Gemini 3 Flash Preview vs Kimi K2 (Jul 2025)
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 40.9 on the Noometry Index.
Last verified . 28 shared benchmarks.
GoogleSummary
- They share 28 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 9 categories and Kimi K2 (Jul 2025) in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 22.7.
- The biggest single-benchmark swing is SimpleBench: 61.1% for Gemini 3 Flash Preview and 26.3% for Kimi K2 (Jul 2025).
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $0.50 / $3 for Gemini 3 Flash Preview.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 262K.
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.
Side by side
| Gemini 3 Flash Preview | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | Moonshot AI | |
| Noometry Index | 52.3 | 40.9 |
| Released | 2025-12-17 | 2025-07-12 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 262K |
| Input $ / M tokens | $0.50 | $0.57 |
| Output $ / M tokens | $3 | $2.30 |
| Results tracked | 59 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 51.5 (#35), Kimi K2 (Jul 2025): 43.1 (#83)
| Benchmark | Gemini 3 Flash Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| SWE-bench Verified (bash only) | 75.8% | 63.4% |
| GSO | 9.8% | 4.9% |
| WeirdML | 61.6% | 42.8% |
| LMArena Coding | 1460 | 1399 |
| ALE-Bench | 1,367 | 597.5 |
| SWE-bench Verified | 75.4% | — |
| Aider Polyglot | — | 59.1% |
| LMArena WebDev | 1439 | — |
| SWE-bench Multilingual | 72.7% | — |
Agentic & Tool Use Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 38.6 (#27), Kimi K2 (Jul 2025): 32.2 (#59)
| Benchmark | Gemini 3 Flash Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | 64.3% | 35.7% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 27.3% | — |
| τ²-bench Retail | 76.8% | — |
| τ²-bench Telecom | 91.2% | — |
| DeepResearch Bench | 49.8% | — |
| BALROG | 48.1% | — |
| GDP.pdf | 10% | — |
| LMArena Search | 1198 | — |
| METR Time Horizons | — | 59.2% |
| Vending-Bench 2 | 3,635 | — |
Reasoning Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 49.2 (#35), Kimi K2 (Jul 2025): 22.7 (#173)
| Benchmark | Gemini 3 Flash Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| SimpleBench | 61.1% | 26.3% |
| LMArena Hard Prompts | 1465 | 1384 |
| Epoch Capabilities Index | 151.83 | 146.02 |
| ForecastBench | 58.5 | 60.2 |
| ARC-AGI-2 | 33.6% | — |
| Kagi LLM Benchmark | — | 64.4% |
| NYT Connections (extended) | 83.1% | — |
| ARC-AGI-1 | 84.7% | — |
| Chess Puzzles | 40% | — |
| Mystery Game Puzzles | 26% | — |
| DTBench | 89.1% | — |
| LMCA | 43.1% | — |
Math Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 51.4 (#42), Kimi K2 (Jul 2025): 40.1 (#81)
| Benchmark | Gemini 3 Flash Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Math | 1472 | 1396 |
| FrontierMath (Feb 2025 set) | 35.6% | 21.4% |
| FrontierMath Tier 4 (v1) | 4.2% | 0% |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| ProofBench | 15% | — |
| Omni-MATH | — | 65.4% |
Knowledge Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 58.8 (#30), Kimi K2 (Jul 2025): 36.9 (#153)
| Benchmark | Gemini 3 Flash Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| Vectara Hallucination Rate | 13.5% | 17.9% |
| LMArena Expert | 1461 | 1363 |
| GPQA Diamond | 89.4% | — |
| SimpleQA Verified | 66.8% | — |
| MMLU-Pro | — | 81.9% |
| Confabulations | — | 20.4% |
| GPQA (HELM) | — | 65.3% |
Multimodal Not comparable
Gemini 3 Flash Preview: 45.3 (#15), Kimi K2 (Jul 2025): —
| Benchmark | Gemini 3 Flash Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Vision | 1285 | — |
| GeoBench | 88% | — |
| VPCT | 72.6% | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1413 | — |
Multilingual Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 55.9 (#26), Kimi K2 (Jul 2025): 49.8 (#125)
| Benchmark | Gemini 3 Flash Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1458 | 1372 |
| LMArena Chinese | 1510 | 1416 |
| LMArena French | 1478 | 1379 |
| LMArena German | 1497 | 1386 |
| LMArena Japanese | 1488 | 1349 |
| LMArena Korean | 1443 | 1324 |
| LMArena Russian | 1480 | 1384 |
| LMArena Spanish | 1470 | 1383 |
Instruction Following Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 75.8 (#52), Kimi K2 (Jul 2025): 71.3 (#151)
| Benchmark | Gemini 3 Flash Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Instruction Following | 1437 | 1347 |
| IFEval | — | 85% |
Long Context Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 44.4 (#63), Kimi K2 (Jul 2025): 41.2 (#140)
| Benchmark | Gemini 3 Flash Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Longer Query | 1452 | 1353 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 17.6% |
Writing & Preference Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 65.6 (#44), Kimi K2 (Jul 2025): 62.5 (#76)
| Benchmark | Gemini 3 Flash Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1466 | 1380 |
| LMArena Creative Writing | 1457 | 1349 |
| LMArena Multi-Turn | 1471 | 1371 |
| Short-Story Creative Writing | — | 85.6% |
| EQ-Bench Creative Writing | — | 1666 |
| WildBench | — | 86.2% |
Frequently asked questions
Is Gemini 3 Flash Preview better than Kimi K2 (Jul 2025)?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 40.9 on the Noometry Index.
Which is cheaper, Gemini 3 Flash Preview or Kimi K2 (Jul 2025)?
Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Gemini 3 Flash Preview lists at $0.50 and $3.
Is Gemini 3 Flash Preview or Kimi K2 (Jul 2025) better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 51.5 versus 43.1 in the Noometry coding category.
Which has the bigger context window?
Gemini 3 Flash Preview does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 3 Flash Preview and Kimi K2 (Jul 2025) share?
28 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and Kimi K2 (Jul 2025) has 42.