Model comparison
Gemini 3.1 Pro Preview vs Llama2 70b Steerlm Chat
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 31.8 on the Noometry Index.
Last verified . 9 shared benchmarks.
Google
NVIDIASummary
- They share 9 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 7 categories and Llama2 70b Steerlm Chat in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 20.0.
- Llama2 70b Steerlm Chat has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.1 Pro Preview | Llama2 70b Steerlm Chat | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 56.7 | 31.8 |
| Released | 2026-02-19 | — |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $12 | — |
| Results tracked | 71 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 42.5 (#99), Llama2 70b Steerlm Chat: 29.9 (#300)
| Benchmark | Gemini 3.1 Pro Preview | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Coding | 1484 | 1025 |
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| LMArena WebDev | 1447 | — |
| SciCode | 58.9% | — |
| GSO | 22.6% | — |
| WeirdML | 72.1% | — |
| MirrorCode | 8.9% | — |
| ALE-Bench | 1,161 | — |
| AlgoTune | 2.02 | — |
Agentic & Tool Use Not comparable
Gemini 3.1 Pro Preview: 37.7 (#34), Llama2 70b Steerlm Chat: —
| Benchmark | Gemini 3.1 Pro Preview | Llama2 70b Steerlm Chat |
|---|---|---|
| Terminal-Bench | 80.2% | — |
| APEX-Agents | 35.3% | — |
| τ²-bench Banking | 26% | — |
| DeepResearch Bench | 47.8% | — |
| PostTrainBench | 22% | — |
| BALROG | 57% | — |
| ExploitBench | 26.1% | — |
| GBAEval | 0.8% | — |
| GDP.pdf | 17% | — |
| LMArena Search | 1211 | — |
| METR Time Horizons | 77% | — |
| Vending-Bench 2 | 3,774 | — |
Reasoning Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 71.7 (#12), Llama2 70b Steerlm Chat: 20.0 (#246)
| Benchmark | Gemini 3.1 Pro Preview | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Hard Prompts | 1485 | 1047 |
| ARC-AGI-2 | 77.1% | — |
| SimpleBench | 79.6% | — |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | 98% | — |
| CritPt | 17.7% | — |
| Chess Puzzles | 55% | — |
| EnigmaEval | 36.8% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.1% | — |
| LMCA | 53.8% | — |
| Epoch Capabilities Index | 154.77 | — |
| ForecastBench | 59 | — |
Math Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 62.1 (#34), Llama2 70b Steerlm Chat: 31.3 (#226)
| Benchmark | Gemini 3.1 Pro Preview | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | 1485 | 1072 |
| FrontierMath (Tiers 1-3) | 59.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| ProofBench | 26% | — |
| FrontierMath (Feb 2025 set) | 36.9% | — |
| FrontierMath Tier 4 (v1) | 16.7% | — |
Knowledge Not comparable
Gemini 3.1 Pro Preview: 71.8 (#3), Llama2 70b Steerlm Chat: —
| Benchmark | Gemini 3.1 Pro Preview | Llama2 70b Steerlm Chat |
|---|---|---|
| GPQA Diamond | 94.4% | — |
| Humanity's Last Exam | 46.4% | — |
| SimpleQA Verified | 73.5% | — |
| Vectara Hallucination Rate | 10.4% | — |
| LMArena Expert | 1485 | — |
Multimodal Not comparable
Gemini 3.1 Pro Preview: 37.9 (#69), Llama2 70b Steerlm Chat: —
| Benchmark | Gemini 3.1 Pro Preview | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Vision | 1296 | — |
| Blueprint-Bench 2 | 26.5% | — |
| Furniture Assembly | 26.7% | — |
| LMArena Document | 1444 | — |
Multilingual Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 57.0 (#12), Llama2 70b Steerlm Chat: 28.8 (#270)
| Benchmark | Gemini 3.1 Pro Preview | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | 1477 | 1063 |
| LMArena Chinese | 1529 | — |
| LMArena French | 1487 | — |
| LMArena German | 1491 | — |
| LMArena Japanese | 1493 | — |
| LMArena Korean | 1455 | — |
| LMArena Russian | 1498 | — |
| LMArena Spanish | 1479 | — |
Instruction Following Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 77.0 (#32), Llama2 70b Steerlm Chat: 54.2 (#279)
| Benchmark | Gemini 3.1 Pro Preview | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | 1466 | 1060 |
Long Context Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 47.4 (#18), Llama2 70b Steerlm Chat: 30.4 (#288)
| Benchmark | Gemini 3.1 Pro Preview | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | 1483 | 998 |
| CL-bench | 20.8% | — |
| CL-bench Life | 16.9% | — |
Writing & Preference Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 66.1 (#37), Llama2 70b Steerlm Chat: 31.6 (#283)
| Benchmark | Gemini 3.1 Pro Preview | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | 1481 | 1098 |
| LMArena Creative Writing | 1482 | 1091 |
| LMArena Multi-Turn | 1488 | 1058 |
| EQ-Bench Creative Writing | 1491 | — |
| EQ-Bench 4 | 1142 | — |
Frequently asked questions
Is Gemini 3.1 Pro Preview better than Llama2 70b Steerlm Chat?
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 31.8 on the Noometry Index.
Is Gemini 3.1 Pro Preview or Llama2 70b Steerlm Chat better for coding?
Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 29.9 in the Noometry coding category.
How many benchmarks do Gemini 3.1 Pro Preview and Llama2 70b Steerlm Chat share?
9 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Llama2 70b Steerlm Chat has 9.