Model comparison
Gemini 1.5 Pro (May 2024) vs Kimi K3
Kimi K3 is the stronger model overall, scoring 59.5 to 32.1 on the Noometry Index.
Last verified . 25 shared benchmarks.
GoogleSummary
- They share 25 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 0 categories and Kimi K3 in 10 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K3 leads 63.0 to 12.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 23.1% for Gemini 1.5 Pro (May 2024) and 97.2% for Kimi K3.
- Kimi K3 has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | Kimi K3 | |
|---|---|---|
| Provider | Moonshot AI | |
| Noometry Index | 32.1 | 59.5 |
| Released | 2024-02-15 | 2026-07-16 |
| Weights | Proprietary | Open |
| Context window | — | 1.05M |
| Max output | — | 1.05M |
| Input $ / M tokens | — | $3 |
| Output $ / M tokens | — | $15 |
| Results tracked | 45 | 53 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), Kimi K3: 61.0 (#10)
| Benchmark | Gemini 1.5 Pro (May 2024) | Kimi K3 |
|---|---|---|
| WeirdML | 22.2% | 82.6% |
| LMArena Coding | 1294 | 1508 |
| DeepSWE | — | 68.5% |
| FrontierCode | — | 44.2% |
| LMArena WebDev | — | 1654 |
| FrontierSWE | — | 25.9% |
| SciCode | — | 59.5% |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| ALE-Bench | — | 1,524 |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use Kimi K3 leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), Kimi K3: 41.8 (#20)
| Benchmark | Gemini 1.5 Pro (May 2024) | Kimi K3 |
|---|---|---|
| APEX-Agents | — | 50.6% |
| TheAgentCompany | 3.4% | — |
| τ²-bench Banking | — | 37.1% |
| Cybench | 7.5% | — |
| PostTrainBench | — | 32% |
| BALROG | 21% | — |
| GBAEval | — | 48.3% |
| GDP.pdf | — | 19% |
| Vending-Bench 2 | — | 5,165 |
Reasoning Kimi K3 leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), Kimi K3: 63.0 (#17)
| Benchmark | Gemini 1.5 Pro (May 2024) | Kimi K3 |
|---|---|---|
| ARC-AGI-2 | 0.8% | 60.4% |
| SimpleBench | 27.1% | 60.7% |
| LMArena Hard Prompts | 1296 | 1496 |
| DTBench | 59% | 91.2% |
| Epoch Capabilities Index | 131.73 | 157.45 |
| ForecastBench | 58.4 | 61.1 |
| NYT Connections (extended) | — | 93.6% |
| ARC-AGI-1 | — | 94.5% |
| CritPt | — | 23.4% |
| Chess Puzzles | — | 39% |
| Mystery Game Puzzles | — | 26% |
| LMCA | — | 52.7% |
| Surface Evolver Bench | — | 95% |
| BIG-Bench Hard | 89.2% | — |
Math Kimi K3 leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), Kimi K3: 74.2 (#16)
| Benchmark | Gemini 1.5 Pro (May 2024) | Kimi K3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 97.2% |
| LMArena Math | 1315 | 1491 |
| FrontierMath (Tiers 1-3) | — | 72.2% |
| FrontierMath Tier 4 | — | 39% |
| MathArena Final-Answer Competitions | — | 87.8% |
| ProofBench | — | 87% |
| Omni-MATH | 36.4% | — |
| MATH Level 5 | 70.4% | — |
Knowledge Kimi K3 leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), Kimi K3: 63.2 (#21)
| Benchmark | Gemini 1.5 Pro (May 2024) | Kimi K3 |
|---|---|---|
| GPQA Diamond | 57.2% | 93.1% |
| LMArena Expert | 1279 | 1521 |
| Humanity's Last Exam | 4.6% | — |
| SimpleQA Verified | — | 50.6% |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| GPQA (HELM) | 53.4% | — |
| MMLU | 86.9% | — |
Multimodal Too close to call
Gemini 1.5 Pro (May 2024): 36.8 (#77), Kimi K3: 37.8 (#70)
| Benchmark | Gemini 1.5 Pro (May 2024) | Kimi K3 |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
| Blueprint-Bench 2 | — | 29.5% |
| Furniture Assembly | — | 34.2% |
Multilingual Kimi K3 leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), Kimi K3: 56.3 (#21)
| Benchmark | Gemini 1.5 Pro (May 2024) | Kimi K3 |
|---|---|---|
| LMArena Non-English | 1312 | 1466 |
| LMArena Chinese | 1331 | 1529 |
| LMArena French | 1302 | 1491 |
| LMArena German | 1286 | 1488 |
| LMArena Japanese | 1292 | 1487 |
| LMArena Korean | 1298 | 1458 |
| LMArena Russian | 1320 | 1482 |
| LMArena Spanish | 1311 | 1472 |
Instruction Following Kimi K3 leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), Kimi K3: 77.7 (#14)
| Benchmark | Gemini 1.5 Pro (May 2024) | Kimi K3 |
|---|---|---|
| LMArena Instruction Following | 1297 | 1483 |
| IFEval | 83.7% | — |
Long Context Kimi K3 leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), Kimi K3: 45.8 (#29)
| Benchmark | Gemini 1.5 Pro (May 2024) | Kimi K3 |
|---|---|---|
| LMArena Longer Query | 1308 | 1494 |
Writing & Preference Kimi K3 leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), Kimi K3: 76.6 (#4)
| Benchmark | Gemini 1.5 Pro (May 2024) | Kimi K3 |
|---|---|---|
| LMArena Text | 1319 | 1476 |
| LMArena Creative Writing | 1333 | 1454 |
| LMArena Multi-Turn | 1296 | 1488 |
| EQ-Bench Creative Writing | — | 2082 |
| WildBench | 81.3% | — |
| EQ-Bench 4 | — | 1339 |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Kimi K3?
Kimi K3 is the stronger model overall, scoring 59.5 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or Kimi K3 better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Kimi K3 share?
25 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Kimi K3 has 53.