Model comparison
Gemini 2.5 Pro vs Llama 3.1-405B
Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 30.4 on the Noometry Index.
Last verified . 34 shared benchmarks.
Google
MetaSummary
- They share 34 benchmarks with published results for both. Gemini 2.5 Pro 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 knowledge, where Gemini 2.5 Pro leads 55.8 to 30.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 84.7% for Gemini 2.5 Pro 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 Pro | Llama 3.1-405B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 44.9 | 30.4 |
| Released | 2025-03-25 | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 78 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Pro leads
Gemini 2.5 Pro: 42.8 (#86), Llama 3.1-405B: 32.7 (#257)
| Benchmark | Gemini 2.5 Pro | Llama 3.1-405B |
|---|---|---|
| WeirdML | 54% | 21.4% |
| LMArena Coding | 1452 | 1291 |
| SWE-bench Verified | 57.6% | — |
| SWE-bench Verified (bash only) | 53.6% | — |
| Aider Polyglot | 83.1% | — |
| LMArena WebDev | 1227 | — |
| SciCode | 42.8% | — |
| GSO | 3.9% | — |
| LiveBench Coding | 85.9% | — |
| CadEval | 64% | — |
| ALE-Bench | 785.52 | — |
| AlgoTune | 1.51 | — |
Agentic & Tool Use Gemini 2.5 Pro leads
Gemini 2.5 Pro: 29.1 (#81), Llama 3.1-405B: 20.9 (#131)
| Benchmark | Gemini 2.5 Pro | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | 30.3% | 7.4% |
| Terminal-Bench | 32.6% | — |
| GDPval | 23.3% | — |
| Remote Labor Index | 0.8% | — |
| τ²-bench Banking | 13.7% | — |
| Cybench | — | 7.5% |
| DeepResearch Bench | 42.8% | — |
| BALROG | 43.3% | — |
| LMArena Search | 1142 | — |
| METR Time Horizons | 55.4% | — |
| Vending-Bench 2 | 573.64 | — |
Reasoning Gemini 2.5 Pro leads
Gemini 2.5 Pro: 28.8 (#85), Llama 3.1-405B: 16.4 (#293)
| Benchmark | Gemini 2.5 Pro | Llama 3.1-405B |
|---|---|---|
| SimpleBench | 62.4% | 23% |
| Kagi LLM Benchmark | 70.3% | 45% |
| LMArena Hard Prompts | 1455 | 1270 |
| DTBench | 82.4% | 61.4% |
| Epoch Capabilities Index | 145.32 | 128.76 |
| ForecastBench | 61.3 | 59.9 |
| ARC-AGI-2 | 4.9% | — |
| ARC-AGI-1 | 41% | — |
| CritPt | 2% | — |
| Chess Puzzles | 20% | — |
| EnigmaEval | 5.6% | — |
| LiveBench Reasoning | 89.8% | — |
| LiveBench Data Analysis | 79.9% | — |
| LMCA | 34.8% | — |
| BIG-Bench Hard | — | 82.9% |
| HellaSwag | — | 89.2% |
| LiveBench | 82.3% | — |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math Gemini 2.5 Pro leads
Gemini 2.5 Pro: 31.9 (#191), Llama 3.1-405B: 17.3 (#283)
| Benchmark | Gemini 2.5 Pro | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 84.7% | 9.7% |
| Omni-MATH | 41.6% | 24.9% |
| LMArena Math | 1450 | 1281 |
| MATH Level 5 | 95.9% | 49.8% |
| FrontierMath (Tiers 1-3) | 24.6% | — |
| FrontierMath Tier 4 | 0% | — |
| LiveBench Math | 90.2% | — |
| FrontierMath (Feb 2025 set) | 14.1% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemini 2.5 Pro leads
Gemini 2.5 Pro: 55.8 (#41), Llama 3.1-405B: 30.4 (#221)
| Benchmark | Gemini 2.5 Pro | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 85.3% | 50.9% |
| MMLU-Pro | 86.3% | 72.3% |
| Confabulations | 10.6% | 17.6% |
| GPQA (HELM) | 74.9% | 52.2% |
| LMArena Expert | 1452 | 1243 |
| Humanity's Last Exam | 21.6% | — |
| Vectara Hallucination Rate | 7% | — |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |
Multimodal Not comparable
Gemini 2.5 Pro: 44.5 (#16), Llama 3.1-405B: —
| Benchmark | Gemini 2.5 Pro | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 1263 | — |
| GeoBench | 86% | — |
| VPCT | 48% | — |
| LMArena Document | 1421 | — |
| SpatialViz-Bench | 44.7% | — |
Multilingual Gemini 2.5 Pro leads
Gemini 2.5 Pro: 55.5 (#30), Llama 3.1-405B: 40.9 (#209)
| Benchmark | Gemini 2.5 Pro | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1452 | 1248 |
| LMArena Chinese | 1507 | 1242 |
| LMArena French | 1473 | 1278 |
| LMArena German | 1487 | 1252 |
| LMArena Japanese | 1462 | 1208 |
| LMArena Korean | 1435 | 1184 |
| LMArena Russian | 1460 | 1265 |
| LMArena Spanish | 1473 | 1259 |
Instruction Following Gemini 2.5 Pro leads
Gemini 2.5 Pro: 75.2 (#71), Llama 3.1-405B: 66.1 (#209)
| Benchmark | Gemini 2.5 Pro | Llama 3.1-405B |
|---|---|---|
| IFEval | 84% | 81.1% |
| LMArena Instruction Following | 1436 | 1259 |
| LiveBench Instruction Following | 80.6% | — |
Long Context Gemini 2.5 Pro leads
Gemini 2.5 Pro: 59.7 (#5), Llama 3.1-405B: 38.4 (#192)
| Benchmark | Gemini 2.5 Pro | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1449 | 1266 |
| Fiction.LiveBench | 91.7% | — |
Writing & Preference Gemini 2.5 Pro leads
Gemini 2.5 Pro: 63.9 (#60), Llama 3.1-405B: 39.1 (#246)
| Benchmark | Gemini 2.5 Pro | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1458 | 1284 |
| LMArena Creative Writing | 1453 | 1262 |
| EQ-Bench Creative Writing | 1421 | 870 |
| WildBench | 85.7% | 78.3% |
| LMArena Multi-Turn | 1453 | 1297 |
| Short-Story Creative Writing | 83.8% | — |
| LiveBench Language | 67.8% | — |
Frequently asked questions
Is Gemini 2.5 Pro better than Llama 3.1-405B?
Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 30.4 on the Noometry Index.
Is Gemini 2.5 Pro or Llama 3.1-405B better for coding?
Gemini 2.5 Pro scores higher on coding benchmarks: 42.8 versus 32.7 in the Noometry coding category.
How many benchmarks do Gemini 2.5 Pro and Llama 3.1-405B share?
34 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Llama 3.1-405B has 42.