Model comparison
Gemini 2.5 Flash vs Llama 3.1-405B
Gemini 2.5 Flash is the stronger model overall, scoring 39.0 to 30.4 on the Noometry Index.
Last verified . 32 shared benchmarks.
Google
MetaSummary
- They share 32 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 9 categories and Llama 3.1-405B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.5 Flash leads 38.1 to 17.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 73.1% for Gemini 2.5 Flash and 9.7% for Llama 3.1-405B.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash | Llama 3.1-405B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 39.0 | 30.4 |
| Released | 2025-04-17 | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 54 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Flash leads
Gemini 2.5 Flash: 35.5 (#210), Llama 3.1-405B: 32.7 (#257)
| Benchmark | Gemini 2.5 Flash | Llama 3.1-405B |
|---|---|---|
| WeirdML | 41.9% | 21.4% |
| LMArena Coding | 1424 | 1291 |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| ALE-Bench | 661.88 | — |
Agentic & Tool Use Gemini 2.5 Flash leads
Gemini 2.5 Flash: 30.6 (#67), Llama 3.1-405B: 20.9 (#131)
| Benchmark | Gemini 2.5 Flash | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | 41.1% | 7.4% |
| Terminal-Bench | 17.1% | — |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| Cybench | — | 7.5% |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |
Reasoning Gemini 2.5 Flash leads
Gemini 2.5 Flash: 18.2 (#271), Llama 3.1-405B: 16.4 (#293)
| Benchmark | Gemini 2.5 Flash | Llama 3.1-405B |
|---|---|---|
| SimpleBench | 41.2% | 23% |
| Kagi LLM Benchmark | 56.8% | 45% |
| LMArena Hard Prompts | 1422 | 1270 |
| DTBench | 76.5% | 61.4% |
| Epoch Capabilities Index | 143.04 | 128.76 |
| ForecastBench | 60.6 | 59.9 |
| ARC-AGI-2 | 2.5% | — |
| ARC-AGI-1 | 33.3% | — |
| CritPt | 1.1% | — |
| EnigmaEval | 2.7% | — |
| LMCA | 27.5% | — |
| BIG-Bench Hard | — | 82.9% |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math Gemini 2.5 Flash leads
Gemini 2.5 Flash: 38.1 (#87), Llama 3.1-405B: 17.3 (#283)
| Benchmark | Gemini 2.5 Flash | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 9.7% |
| Omni-MATH | 38.5% | 24.9% |
| LMArena Math | 1415 | 1281 |
| MATH Level 5 | — | 49.8% |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemini 2.5 Flash leads
Gemini 2.5 Flash: 36.1 (#162), Llama 3.1-405B: 30.4 (#221)
| Benchmark | Gemini 2.5 Flash | Llama 3.1-405B |
|---|---|---|
| MMLU-Pro | 63.9% | 72.3% |
| Confabulations | 16.8% | 17.6% |
| GPQA (HELM) | 39% | 52.2% |
| LMArena Expert | 1426 | 1243 |
| GPQA Diamond | — | 50.9% |
| Humanity's Last Exam | 12.1% | — |
| Vectara Hallucination Rate | 7.8% | — |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |
Multimodal Not comparable
Gemini 2.5 Flash: 41.2 (#31), Llama 3.1-405B: —
| Benchmark | Gemini 2.5 Flash | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 1254 | — |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Gemini 2.5 Flash leads
Gemini 2.5 Flash: 52.5 (#83), Llama 3.1-405B: 40.9 (#209)
| Benchmark | Gemini 2.5 Flash | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1410 | 1248 |
| LMArena Chinese | 1450 | 1242 |
| LMArena French | 1433 | 1278 |
| LMArena German | 1419 | 1252 |
| LMArena Japanese | 1403 | 1208 |
| LMArena Korean | 1385 | 1184 |
| LMArena Russian | 1415 | 1265 |
| LMArena Spanish | 1421 | 1259 |
Instruction Following Gemini 2.5 Flash leads
Gemini 2.5 Flash: 75.9 (#50), Llama 3.1-405B: 66.1 (#209)
| Benchmark | Gemini 2.5 Flash | Llama 3.1-405B |
|---|---|---|
| IFEval | 89.8% | 81.1% |
| LMArena Instruction Following | 1405 | 1259 |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#16), Llama 3.1-405B: 38.4 (#192)
| Benchmark | Gemini 2.5 Flash | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1419 | 1266 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference Gemini 2.5 Flash leads
Gemini 2.5 Flash: 54.0 (#153), Llama 3.1-405B: 39.1 (#246)
| Benchmark | Gemini 2.5 Flash | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1417 | 1284 |
| LMArena Creative Writing | 1400 | 1262 |
| EQ-Bench Creative Writing | 1137 | 870 |
| WildBench | 81.7% | 78.3% |
| LMArena Multi-Turn | 1408 | 1297 |
| Short-Story Creative Writing | 76.5% | — |
Frequently asked questions
Is Gemini 2.5 Flash better than Llama 3.1-405B?
Gemini 2.5 Flash is the stronger model overall, scoring 39.0 to 30.4 on the Noometry Index.
Is Gemini 2.5 Flash or Llama 3.1-405B better for coding?
Gemini 2.5 Flash scores higher on coding benchmarks: 35.5 versus 32.7 in the Noometry coding category.
How many benchmarks do Gemini 2.5 Flash and Llama 3.1-405B share?
32 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Llama 3.1-405B has 42.