Model comparison
Gemini 2.5 Flash vs Grok 3
Gemini 2.5 Flash and Grok 3 score almost the same on the Noometry Index (39.3 vs 39.9), so choose on price, context window or the category you care about most.
Last verified . 38 shared benchmarks.
GoogleSummary
- They share 38 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 5 categories and Grok 3 in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 3 leads 46.2 to 36.4.
- The biggest single-benchmark swing is ARC-AGI-1: 33.3% for Gemini 2.5 Flash and 5.5% for Grok 3.
Side by side
| Gemini 2.5 Flash | Grok 3 | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 39.3 | 39.9 |
| Released | 2025-04-17 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 54 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Gemini 2.5 Flash: 35.8 (#220), Grok 3: 41.9 (#115)
| Benchmark | Gemini 2.5 Flash | Grok 3 |
|---|---|---|
| Aider Polyglot | 55.1% | 53.3% |
| WeirdML | 41.9% | 37.2% |
| LMArena Coding | 1424 | 1432 |
| SWE-bench Verified (bash only) | 28.7% | — |
| ALE-Bench | 661.88 | — |
Agentic & Tool Use Too close to call
Gemini 2.5 Flash: 30.8 (#74), Grok 3: 30.5 (#76)
| Benchmark | Gemini 2.5 Flash | Grok 3 |
|---|---|---|
| BALROG | 33.5% | 29.5% |
| Terminal-Bench | 17.1% | — |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| Vending-Bench 2 | 548.84 | — |
Reasoning Gemini 2.5 Flash leads
Gemini 2.5 Flash: 18.1 (#286), Grok 3: 13.7 (#333)
| Benchmark | Gemini 2.5 Flash | Grok 3 |
|---|---|---|
| ARC-AGI-2 | 2.5% | 0% |
| SimpleBench | 41.2% | 36.1% |
| Kagi LLM Benchmark | 56.8% | 61.3% |
| ARC-AGI-1 | 33.3% | 5.5% |
| LMArena Hard Prompts | 1422 | 1434 |
| Epoch Capabilities Index | 143.03 | 138.33 |
| CritPt | 1.1% | — |
| EnigmaEval | 2.7% | — |
| DTBench | 76.5% | — |
| LMCA | 27.5% | — |
| ForecastBench | 60.6 | — |
Math Gemini 2.5 Flash leads
Gemini 2.5 Flash: 39.9 (#98), Grok 3: 38.0 (#145)
| Benchmark | Gemini 2.5 Flash | Grok 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 55.6% |
| Omni-MATH | 38.5% | 46.4% |
| LMArena Math | 1415 | 1391 |
| FrontierMath (Feb 2025 set) | 4.8% | 3.8% |
| FrontierMath Tier 4 (v1) | 4.2% | 0% |
| MATH Level 5 | — | 88.7% |
Knowledge Grok 3 leads
Gemini 2.5 Flash: 36.4 (#168), Grok 3: 46.2 (#82)
| Benchmark | Gemini 2.5 Flash | Grok 3 |
|---|---|---|
| MMLU-Pro | 63.9% | 78.8% |
| Confabulations | 16.8% | 14.2% |
| Vectara Hallucination Rate | 7.8% | 5.8% |
| GPQA (HELM) | 39% | 65% |
| LMArena Expert | 1426 | 1421 |
| GPQA Diamond | — | 75.8% |
| Humanity's Last Exam | 12.1% | — |
Multimodal Not comparable
Gemini 2.5 Flash: 41.8 (#32), Grok 3: —
| Benchmark | Gemini 2.5 Flash | Grok 3 |
|---|---|---|
| LMArena Vision | 1253 | — |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Too close to call
Gemini 2.5 Flash: 52.3 (#88), Grok 3: 52.3 (#87)
| Benchmark | Gemini 2.5 Flash | Grok 3 |
|---|---|---|
| LMArena Non-English | 1409 | 1410 |
| LMArena Chinese | 1450 | 1448 |
| LMArena French | 1433 | 1460 |
| LMArena German | 1418 | 1431 |
| LMArena Japanese | 1405 | 1387 |
| LMArena Korean | 1385 | 1373 |
| LMArena Russian | 1415 | 1416 |
| LMArena Spanish | 1421 | 1417 |
Instruction Following Too close to call
Gemini 2.5 Flash: 75.7 (#54), Grok 3: 75.0 (#73)
| Benchmark | Gemini 2.5 Flash | Grok 3 |
|---|---|---|
| IFEval | 89.8% | 88.4% |
| LMArena Instruction Following | 1405 | 1409 |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#17), Grok 3: 38.7 (#192)
| Benchmark | Gemini 2.5 Flash | Grok 3 |
|---|---|---|
| Fiction.LiveBench | 77.8% | 58.3% |
| LMArena Longer Query | 1419 | 1439 |
Writing & Preference Grok 3 leads
Gemini 2.5 Flash: 53.8 (#157), Grok 3: 55.8 (#141)
| Benchmark | Gemini 2.5 Flash | Grok 3 |
|---|---|---|
| LMArena Text | 1417 | 1426 |
| LMArena Creative Writing | 1400 | 1414 |
| Short-Story Creative Writing | 76.5% | 76.4% |
| EQ-Bench Creative Writing | 1137 | 1186 |
| WildBench | 81.7% | 84.9% |
| LMArena Multi-Turn | 1408 | 1425 |
Frequently asked questions
Is Gemini 2.5 Flash better than Grok 3?
Gemini 2.5 Flash and Grok 3 score almost the same on the Noometry Index (39.3 vs 39.9), so choose on price, context window or the category you care about most.
Is Gemini 2.5 Flash or Grok 3 better for coding?
Grok 3 scores higher on coding benchmarks: 41.9 versus 35.8 in the Noometry coding category.
How many benchmarks do Gemini 2.5 Flash and Grok 3 share?
38 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Grok 3 has 40.