Model comparison
Gemini 2.5 Flash vs Grok 4.6
Grok 4.6 is the stronger model overall, scoring 56.9 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 3.5× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
GoogleSummary
- They share 29 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 2 categories and Grok 4.6 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.6 leads 61.4 to 18.1.
- The biggest single-benchmark swing is ARC-AGI-2: 2.5% for Gemini 2.5 Flash and 67.1% for Grok 4.6.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $2 / $6 for Grok 4.6.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 500K.
Side by side
| Gemini 2.5 Flash | Grok 4.6 | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 39.3 | 56.9 |
| Released | 2025-04-17 | 2026-08-12 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 500K |
| Max output | 66K | 500K |
| Input $ / M tokens | $0.30 | $2 |
| Output $ / M tokens | $2.50 | $6 |
| Results tracked | 54 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
Gemini 2.5 Flash: 35.8 (#220), Grok 4.6: 58.5 (#16)
| Benchmark | Gemini 2.5 Flash | Grok 4.6 |
|---|---|---|
| WeirdML | 41.9% | 67.3% |
| LMArena Coding | 1424 | 1465 |
| ALE-Bench | 661.88 | 1,508 |
| DeepSWE | — | 67.5% |
| FrontierCode | — | 48% |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| CursorBench | — | 41.4% |
| LMArena WebDev | — | 1617 |
| FrontierSWE | — | 25.3% |
| SciCode | — | 56.5% |
Agentic & Tool Use Grok 4.6 leads
Gemini 2.5 Flash: 30.8 (#74), Grok 4.6: 39.4 (#27)
| Benchmark | Gemini 2.5 Flash | Grok 4.6 |
|---|---|---|
| Vending-Bench 2 | 548.84 | 9,047 |
| Terminal-Bench | 17.1% | — |
| APEX-Agents | — | 65.3% |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| GDP.pdf | — | 17.2% |
Reasoning Grok 4.6 leads
Gemini 2.5 Flash: 18.1 (#286), Grok 4.6: 61.4 (#20)
| Benchmark | Gemini 2.5 Flash | Grok 4.6 |
|---|---|---|
| ARC-AGI-2 | 2.5% | 67.1% |
| SimpleBench | 41.2% | 75.9% |
| ARC-AGI-1 | 33.3% | 87.5% |
| CritPt | 1.1% | 19.7% |
| LMArena Hard Prompts | 1422 | 1447 |
| DTBench | 76.5% | 97.3% |
| LMCA | 27.5% | 48.5% |
| Epoch Capabilities Index | 143.03 | 156.44 |
| Kagi LLM Benchmark | 56.8% | — |
| NYT Connections (extended) | — | 80% |
| Chess Puzzles | — | 40% |
| EnigmaEval | 2.7% | — |
| EBR-Bench | — | 30.5% |
| Mystery Game Puzzles | — | 34% |
| ForecastBench | 60.6 | — |
Math Grok 4.6 leads
Gemini 2.5 Flash: 39.9 (#98), Grok 4.6: 67.0 (#24)
| Benchmark | Gemini 2.5 Flash | Grok 4.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 99.2% |
| LMArena Math | 1415 | 1423 |
| FrontierMath (Tiers 1-3) | — | 66% |
| FrontierMath Tier 4 | — | 31.7% |
| ProofBench | — | 51% |
| Omni-MATH | 38.5% | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Grok 4.6 leads
Gemini 2.5 Flash: 36.4 (#168), Grok 4.6: 63.3 (#20)
| Benchmark | Gemini 2.5 Flash | Grok 4.6 |
|---|---|---|
| LMArena Expert | 1426 | 1467 |
| GPQA Diamond | — | 94% |
| Humanity's Last Exam | 12.1% | — |
| SimpleQA Verified | — | 49.3% |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| Vectara Hallucination Rate | 7.8% | — |
| GPQA (HELM) | 39% | — |
Multimodal Grok 4.6 leads
Gemini 2.5 Flash: 41.8 (#32), Grok 4.6: 43.6 (#23)
| Benchmark | Gemini 2.5 Flash | Grok 4.6 |
|---|---|---|
| LMArena Vision | 1253 | 1263 |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| Blueprint-Bench 2 | — | 33.2% |
| Furniture Assembly | — | 40% |
| LMArena Document | — | 1452 |
| SpatialViz-Bench | 36.9% | — |
Multilingual Too close to call
Gemini 2.5 Flash: 52.3 (#88), Grok 4.6: 53.0 (#74)
| Benchmark | Gemini 2.5 Flash | Grok 4.6 |
|---|---|---|
| LMArena Non-English | 1409 | 1420 |
| LMArena Chinese | 1450 | 1480 |
| LMArena French | 1433 | 1461 |
| LMArena German | 1418 | 1431 |
| LMArena Japanese | 1405 | 1376 |
| LMArena Korean | 1385 | 1397 |
| LMArena Russian | 1415 | 1422 |
| LMArena Spanish | 1421 | 1404 |
Instruction Following Too close to call
Gemini 2.5 Flash: 75.7 (#54), Grok 4.6: 75.4 (#63)
| Benchmark | Gemini 2.5 Flash | Grok 4.6 |
|---|---|---|
| LMArena Instruction Following | 1405 | 1431 |
| IFEval | 89.8% | — |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#17), Grok 4.6: 44.5 (#66)
| Benchmark | Gemini 2.5 Flash | Grok 4.6 |
|---|---|---|
| LMArena Longer Query | 1419 | 1454 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference Grok 4.6 leads
Gemini 2.5 Flash: 53.8 (#157), Grok 4.6: 62.3 (#80)
| Benchmark | Gemini 2.5 Flash | Grok 4.6 |
|---|---|---|
| LMArena Text | 1417 | 1428 |
| LMArena Creative Writing | 1400 | 1428 |
| LMArena Multi-Turn | 1408 | 1425 |
| Short-Story Creative Writing | 76.5% | — |
| EQ-Bench Creative Writing | 1137 | — |
| WildBench | 81.7% | — |
Frequently asked questions
Is Gemini 2.5 Flash better than Grok 4.6?
Grok 4.6 is the stronger model overall, scoring 56.9 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 3.5× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 Flash or Grok 4.6?
Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Grok 4.6 lists at $2 and $6.
Is Gemini 2.5 Flash or Grok 4.6 better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 35.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 500K.
How many benchmarks do Gemini 2.5 Flash and Grok 4.6 share?
29 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Grok 4.6 has 49.