Model comparison
Gemma 3 27B vs Kimi K2 (Jul 2025)
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 30.8 on the Noometry Index. Gemma 3 27B costs 10× less per token, which makes it the better buy when Kimi K2 (Jul 2025)'s lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
GoogleSummary
- They share 26 benchmarks with published results for both. Gemma 3 27B scores higher in 0 categories and Kimi K2 (Jul 2025) in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Kimi K2 (Jul 2025) leads 42.4 to 22.5.
- The biggest single-benchmark swing is Aider Polyglot: 4.9% for Gemma 3 27B and 59.1% for Kimi K2 (Jul 2025).
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.57 / $2.30 for Kimi K2 (Jul 2025).
- Kimi K2 (Jul 2025) accepts more context: 262K tokens versus 131K.
Side by side
| Gemma 3 27B | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | Moonshot AI | |
| Noometry Index | 30.8 | 41.2 |
| Released | 2025-03-11 | 2025-07-12 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 8K | 262K |
| Input $ / M tokens | $0.08 | $0.57 |
| Output $ / M tokens | $0.16 | $2.30 |
| Results tracked | 43 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
Gemma 3 27B: 22.5 (#334), Kimi K2 (Jul 2025): 42.4 (#102)
| Benchmark | Gemma 3 27B | Kimi K2 (Jul 2025) |
|---|---|---|
| Aider Polyglot | 4.9% | 59.1% |
| LMArena Coding | 1322 | 1399 |
| SWE-bench Verified (bash only) | — | 63.4% |
| SciCode | 21.2% | — |
| GSO | — | 4.9% |
| WeirdML | — | 42.8% |
| LiveBench Coding | 39.9% | — |
| ALE-Bench | — | 597.5 |
Agentic & Tool Use Kimi K2 (Jul 2025) leads
Gemma 3 27B: 25.1 (#110), Kimi K2 (Jul 2025): 32.4 (#64)
| Benchmark | Gemma 3 27B | Kimi K2 (Jul 2025) |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | 59.1% |
| Terminal-Bench | — | 35.7% |
| METR Time Horizons | — | 59.2% |
Reasoning Kimi K2 (Jul 2025) leads
Gemma 3 27B: 16.7 (#301), Kimi K2 (Jul 2025): 23.3 (#179)
| Benchmark | Gemma 3 27B | Kimi K2 (Jul 2025) |
|---|---|---|
| Kagi LLM Benchmark | 40.4% | 64.4% |
| LMArena Hard Prompts | 1340 | 1384 |
| Epoch Capabilities Index | 130.04 | 146.01 |
| SimpleBench | — | 26.3% |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| ForecastBench | — | 60.2 |
| LiveBench | 50% | — |
Math Kimi K2 (Jul 2025) leads
Gemma 3 27B: 25.9 (#265), Kimi K2 (Jul 2025): 42.7 (#83)
| Benchmark | Gemma 3 27B | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Math | 1312 | 1397 |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| Omni-MATH | — | 65.4% |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Kimi K2 (Jul 2025) leads
Gemma 3 27B: 25.5 (#261), Kimi K2 (Jul 2025): 37.3 (#157)
| Benchmark | Gemma 3 27B | Kimi K2 (Jul 2025) |
|---|---|---|
| Confabulations | 40.3% | 20.4% |
| Vectara Hallucination Rate | 7.4% | 17.9% |
| LMArena Expert | 1304 | 1365 |
| GPQA Diamond | 47.7% | — |
| MMLU-Pro | — | 81.9% |
| GPQA (HELM) | — | 65.3% |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), Kimi K2 (Jul 2025): —
| Benchmark | Gemma 3 27B | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual Kimi K2 (Jul 2025) leads
Gemma 3 27B: 46.9 (#155), Kimi K2 (Jul 2025): 49.6 (#130)
| Benchmark | Gemma 3 27B | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1334 | 1372 |
| LMArena Chinese | 1346 | 1415 |
| LMArena French | 1368 | 1379 |
| LMArena German | 1362 | 1387 |
| LMArena Japanese | 1287 | 1349 |
| LMArena Korean | 1308 | 1325 |
| LMArena Russian | 1349 | 1385 |
| LMArena Spanish | 1349 | 1386 |
Instruction Following Too close to call
Gemma 3 27B: 70.6 (#160), Kimi K2 (Jul 2025): 71.1 (#156)
| Benchmark | Gemma 3 27B | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Instruction Following | 1321 | 1348 |
| LiveBench Instruction Following | 74.9% | — |
| IFEval | — | 85% |
Long Context Kimi K2 (Jul 2025) leads
Gemma 3 27B: 27.6 (#293), Kimi K2 (Jul 2025): 41.2 (#145)
| Benchmark | Gemma 3 27B | Kimi K2 (Jul 2025) |
|---|---|---|
| Fiction.LiveBench | 33.3% | 66.7% |
| LMArena Longer Query | 1333 | 1353 |
| CL-bench | — | 17.6% |
Writing & Preference Kimi K2 (Jul 2025) leads
Gemma 3 27B: 52.5 (#168), Kimi K2 (Jul 2025): 62.3 (#78)
| Benchmark | Gemma 3 27B | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1358 | 1380 |
| LMArena Creative Writing | 1346 | 1350 |
| Short-Story Creative Writing | 79.9% | 85.6% |
| EQ-Bench Creative Writing | 1266 | 1666 |
| LMArena Multi-Turn | 1345 | 1371 |
| WildBench | — | 86.2% |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Kimi K2 (Jul 2025)?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 30.8 on the Noometry Index. Gemma 3 27B costs 10× less per token, which makes it the better buy when Kimi K2 (Jul 2025)'s lead doesn't matter for your workload.
Which is cheaper, Gemma 3 27B or Kimi K2 (Jul 2025)?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Kimi K2 (Jul 2025) lists at $0.57 and $2.30.
Is Gemma 3 27B or Kimi K2 (Jul 2025) better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 22.5 in the Noometry coding category.
Which has the bigger context window?
Kimi K2 (Jul 2025) does, with 262K tokens against 131K.
How many benchmarks do Gemma 3 27B and Kimi K2 (Jul 2025) share?
26 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Kimi K2 (Jul 2025) has 42.