# Gemini 3.7 Flash vs Llama 4 Maverick

> Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 30.9 on the Noometry Index. Llama 4 Maverick costs 4.9× less per token, which makes it the better buy when Gemini 3.7 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-7-flash-vs-llama-4-maverick
- Last updated: 2026-10-12
- Shared benchmarks: 30

## Summary

- They share 30 benchmarks with published results for both. Gemini 3.7 Flash scores higher in 10 categories and Llama 4 Maverick in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.7 Flash leads 70.0 to 10.1.
- The biggest single-benchmark swing is ARC-AGI-1: 95.5% for Gemini 3.7 Flash and 4.4% for Llama 4 Maverick.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.7 Flash.
- Gemini 3.7 Flash accepts more context: 1.05M tokens versus 128K.
- Llama 4 Maverick has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.7 Flash | Llama 4 Maverick |
|---|---|---|
| Provider | Google | Meta |
| Noometry Index | 59.8 | 30.9 |
| Rank | 14 | 282 |
| Context | 1.05M | 128K |
| Input $/M | $0.75 | $0.19 |
| Output $/M | $3.75 | $0.65 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.7 Flash: 56.2 (#22)
- Llama 4 Maverick: 26.6 (#324)

| Benchmark | Gemini 3.7 Flash | Llama 4 Maverick |
|---|---|---|
| SciCode | 59.8% | 33.1% |
| LMArena Coding | 1497 | 1302 |
| ALE-Bench | 904.3 | 172.97 |
| DeepSWE | 65.5% | — |
| FrontierCode | 43.6% | — |
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| LMArena WebDev | 1592 | — |
| FrontierSWE | 20.3% | — |
| WeirdML | — | 24.5% |
| BigCodeBench Instruct | — | 49.7% |
| BigCodeBench Complete | — | 61.4% |

## Agentic & Tool Use

- Gemini 3.7 Flash: 42.1 (#19)
- Llama 4 Maverick: 28.2 (#91)

| Benchmark | Gemini 3.7 Flash | Llama 4 Maverick |
|---|---|---|
| APEX-Agents | 67.8% | — |
| Berkeley Function Calling Leaderboard | — | 37.3% |
| Remote Labor Index | 5% | — |
| GDP.pdf | 23.8% | — |

## Reasoning

- Gemini 3.7 Flash: 70.0 (#15)
- Llama 4 Maverick: 10.1 (#342)

| Benchmark | Gemini 3.7 Flash | Llama 4 Maverick |
|---|---|---|
| ARC-AGI-2 | 84.6% | 0% |
| NYT Connections (extended) | 94% | 8% |
| ARC-AGI-1 | 95.5% | 4.4% |
| CritPt | 14.3% | 0% |
| LMArena Hard Prompts | 1494 | 1281 |
| DTBench | 96.8% | 61.9% |
| LMCA | 50.4% | 15.9% |
| Epoch Capabilities Index | 157.27 | 132.2 |
| SimpleBench | — | 27.7% |
| Kagi LLM Benchmark | — | 55.9% |
| Chess Puzzles | 47% | — |
| EnigmaEval | — | 0.6% |
| Mystery Game Puzzles | 37% | — |
| ForecastBench | — | 57.5 |

## Math

- Gemini 3.7 Flash: 69.6 (#23)
- Llama 4 Maverick: 26.0 (#262)

| Benchmark | Gemini 3.7 Flash | Llama 4 Maverick |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 97.2% | 20.6% |
| LMArena Math | 1507 | 1299 |
| FrontierMath (Tiers 1-3) | 71.6% | — |
| FrontierMath Tier 4 | 36.6% | — |
| ProofBench | 58% | — |
| Omni-MATH | — | 42.2% |
| MATH Level 5 | — | 73% |
| FrontierMath (Feb 2025 set) | — | 0.7% |

## Knowledge

- Gemini 3.7 Flash: 69.7 (#5)
- Llama 4 Maverick: 33.4 (#204)

| Benchmark | Gemini 3.7 Flash | Llama 4 Maverick |
|---|---|---|
| GPQA Diamond | 94.8% | 67% |
| LMArena Expert | 1508 | 1259 |
| Humanity's Last Exam | — | 5.7% |
| SimpleQA Verified | 69.2% | — |
| MMLU-Pro | — | 81% |
| Confabulations | — | 22.6% |
| Vectara Hallucination Rate | — | 8.2% |
| GPQA (HELM) | — | 65% |

## Multimodal

- Gemini 3.7 Flash: 37.3 (#73)
- Llama 4 Maverick: 31.6 (#105)

| Benchmark | Gemini 3.7 Flash | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | 1316 | 1142 |
| GeoBench | — | 52% |
| Furniture Assembly | 26.7% | — |
| SpatialViz-Bench | — | 31.8% |

## Multilingual

- Gemini 3.7 Flash: 57.6 (#7)
- Llama 4 Maverick: 42.2 (#195)

| Benchmark | Gemini 3.7 Flash | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1484 | 1269 |
| LMArena Chinese | 1548 | 1277 |
| LMArena French | 1505 | 1259 |
| LMArena German | 1498 | 1291 |
| LMArena Japanese | 1512 | 1207 |
| LMArena Korean | 1483 | 1203 |
| LMArena Russian | 1516 | 1286 |
| LMArena Spanish | 1503 | 1293 |

## Instruction Following

- Gemini 3.7 Flash: 77.7 (#15)
- Llama 4 Maverick: 71.7 (#146)

| Benchmark | Gemini 3.7 Flash | Llama 4 Maverick |
|---|---|---|
| LMArena Instruction Following | 1483 | 1267 |
| IFEval | — | 90.8% |

## Long Context

- Gemini 3.7 Flash: 45.7 (#30)
- Llama 4 Maverick: 31.4 (#279)

| Benchmark | Gemini 3.7 Flash | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1492 | 1280 |
| Fiction.LiveBench | — | 46.2% |

## Writing & Preference

- Gemini 3.7 Flash: 71.2 (#20)
- Llama 4 Maverick: 38.8 (#252)

| Benchmark | Gemini 3.7 Flash | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1486 | 1287 |
| LMArena Creative Writing | 1490 | 1267 |
| EQ-Bench Creative Writing | 1723 | 860 |
| LMArena Multi-Turn | 1489 | 1289 |
| Short-Story Creative Writing | — | 62% |
| WildBench | — | 80% |

## FAQ

### Is Gemini 3.7 Flash better than Llama 4 Maverick?

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 30.9 on the Noometry Index. Llama 4 Maverick costs 4.9× less per token, which makes it the better buy when Gemini 3.7 Flash's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3.7 Flash or Llama 4 Maverick?

Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; Gemini 3.7 Flash lists at $0.75 and $3.75.

### Is Gemini 3.7 Flash or Llama 4 Maverick better for coding?

Gemini 3.7 Flash scores higher on coding benchmarks: 56.2 versus 26.6 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.7 Flash does, with 1.05M tokens against 128K.

### How many benchmarks do Gemini 3.7 Flash and Llama 4 Maverick share?

30 benchmarks have published results for both models. Gemini 3.7 Flash has 44 scored results on Noometry and Llama 4 Maverick has 54.