Model comparison
Gemini 2.0 Flash (Feb 2025) vs Kimi K2 (Jul 2025)
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 35.1 on the Noometry Index.
Last verified . 33 shared benchmarks.
GoogleSummary
- They share 33 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 1 category and Kimi K2 (Jul 2025) in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Kimi K2 (Jul 2025) leads 42.4 to 28.4.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 13.5% for Gemini 2.0 Flash (Feb 2025) and 63.4% for Kimi K2 (Jul 2025).
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash (Feb 2025) | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | Moonshot AI | |
| Noometry Index | 35.1 | 41.2 |
| Released | 2024-12-06 | 2025-07-12 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.57 |
| Output $ / M tokens | — | $2.30 |
| Results tracked | 54 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), Kimi K2 (Jul 2025): 42.4 (#102)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2 (Jul 2025) |
|---|---|---|
| SWE-bench Verified (bash only) | 13.5% | 63.4% |
| Aider Polyglot | 38.2% | 59.1% |
| WeirdML | 25.8% | 42.8% |
| LMArena Coding | 1350 | 1399 |
| GSO | — | 4.9% |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
| ALE-Bench | — | 597.5 |
Agentic & Tool Use Kimi K2 (Jul 2025) leads
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), Kimi K2 (Jul 2025): 32.4 (#64)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | — | 35.7% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| TheAgentCompany | 11.4% | — |
| METR Time Horizons | — | 59.2% |
Reasoning Kimi K2 (Jul 2025) leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), Kimi K2 (Jul 2025): 23.3 (#179)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2 (Jul 2025) |
|---|---|---|
| SimpleBench | 31.1% | 26.3% |
| Kagi LLM Benchmark | 37.8% | 64.4% |
| LMArena Hard Prompts | 1346 | 1384 |
| Epoch Capabilities Index | 135.36 | 146.01 |
| ARC-AGI-2 | 1.3% | — |
| EnigmaEval | 1.1% | — |
| LiveBench Reasoning | 78.2% | — |
| DTBench | 63.2% | — |
| LiveBench Data Analysis | 69.4% | — |
| ForecastBench | — | 60.2 |
| LiveBench | 66.9% | — |
Math Kimi K2 (Jul 2025) leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), Kimi K2 (Jul 2025): 42.7 (#83)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2 (Jul 2025) |
|---|---|---|
| Omni-MATH | 45.9% | 65.4% |
| LMArena Math | 1352 | 1397 |
| FrontierMath (Feb 2025 set) | 1.7% | 21.4% |
| OTIS Mock AIME 2024-2025 | 57.8% | — |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Kimi K2 (Jul 2025) leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), Kimi K2 (Jul 2025): 37.3 (#157)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2 (Jul 2025) |
|---|---|---|
| MMLU-Pro | 73.7% | 81.9% |
| Confabulations | 12.4% | 20.4% |
| GPQA (HELM) | 55.6% | 65.3% |
| LMArena Expert | 1339 | 1365 |
| GPQA Diamond | 64.1% | — |
| Humanity's Last Exam | 6.6% | — |
| Vectara Hallucination Rate | — | 17.9% |
| MMLU | 79.7% | — |
Multimodal Not comparable
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), Kimi K2 (Jul 2025): —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Vision | 1158 | — |
| GeoBench | 77% | — |
Multilingual Kimi K2 (Jul 2025) leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), Kimi K2 (Jul 2025): 49.6 (#130)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1342 | 1372 |
| LMArena Chinese | 1373 | 1415 |
| LMArena French | 1391 | 1379 |
| LMArena German | 1353 | 1387 |
| LMArena Japanese | 1294 | 1349 |
| LMArena Korean | 1313 | 1325 |
| LMArena Russian | 1351 | 1385 |
| LMArena Spanish | 1363 | 1386 |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), Kimi K2 (Jul 2025): 71.1 (#156)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2 (Jul 2025) |
|---|---|---|
| IFEval | 84.1% | 85% |
| LMArena Instruction Following | 1336 | 1348 |
| LiveBench Instruction Following | 85.8% | — |
Long Context Kimi K2 (Jul 2025) leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), Kimi K2 (Jul 2025): 41.2 (#145)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2 (Jul 2025) |
|---|---|---|
| Fiction.LiveBench | 61.1% | 66.7% |
| LMArena Longer Query | 1344 | 1353 |
| CL-bench | — | 17.6% |
Writing & Preference Kimi K2 (Jul 2025) leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), Kimi K2 (Jul 2025): 62.3 (#78)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1354 | 1380 |
| LMArena Creative Writing | 1340 | 1350 |
| Short-Story Creative Writing | 73.8% | 85.6% |
| EQ-Bench Creative Writing | 1128 | 1666 |
| WildBench | 80% | 86.2% |
| LMArena Multi-Turn | 1350 | 1371 |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than Kimi K2 (Jul 2025)?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Kimi K2 (Jul 2025) better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Kimi K2 (Jul 2025) share?
33 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Kimi K2 (Jul 2025) has 42.