Model comparison
Gemini 3.6 Flash vs Llama 2-13B
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 29.1 on the Noometry Index.
Last verified . 20 shared benchmarks.
Google
MetaSummary
- They share 20 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 8 categories and Llama 2-13B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.9 to 12.3.
- The biggest single-benchmark swing is DTBench: 95.5% for Gemini 3.6 Flash and 42.2% for Llama 2-13B.
- Llama 2-13B has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.6 Flash | Llama 2-13B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 54.1 | 29.1 |
| Released | 2026-07-21 | 2023-07-18 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.75 | — |
| Output $ / M tokens | $3.75 | — |
| Results tracked | 46 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.6 Flash leads
Gemini 3.6 Flash: 49.6 (#45), Llama 2-13B: 30.4 (#287)
| Benchmark | Gemini 3.6 Flash | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1492 | 1062 |
| DeepSWE | 46.7% | — |
| FrontierCode | 34.4% | — |
| LMArena WebDev | 1536 | — |
| SciCode | 52.7% | — |
| WeirdML | 56.1% | — |
| ALE-Bench | 715.52 | — |
Agentic & Tool Use Not comparable
Gemini 3.6 Flash: 32.4 (#56), Llama 2-13B: —
| Benchmark | Gemini 3.6 Flash | Llama 2-13B |
|---|---|---|
| APEX-Agents | 46.9% | — |
| GDP.pdf | 14% | — |
Reasoning Gemini 3.6 Flash leads
Gemini 3.6 Flash: 58.9 (#20), Llama 2-13B: 12.3 (#333)
| Benchmark | Gemini 3.6 Flash | Llama 2-13B |
|---|---|---|
| Chess Puzzles | 43% | 0% |
| LMArena Hard Prompts | 1486 | 1051 |
| DTBench | 95.5% | 42.2% |
| Epoch Capabilities Index | 154.36 | 105.8 |
| ARC-AGI-2 | 60.4% | — |
| NYT Connections (extended) | 89% | — |
| ARC-AGI-1 | 91.2% | — |
| CritPt | 10.6% | — |
| Mystery Game Puzzles | 30% | — |
| LMCA | 44.9% | — |
| BIG-Bench Hard | — | 58.2% |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math Gemini 3.6 Flash leads
Gemini 3.6 Flash: 57.0 (#33), Llama 2-13B: 28.7 (#226)
| Benchmark | Gemini 3.6 Flash | Llama 2-13B |
|---|---|---|
| LMArena Math | 1504 | 1065 |
| FrontierMath (Tiers 1-3) | 58.9% | — |
| FrontierMath Tier 4 | 22% | — |
| MathArena Final-Answer Competitions | 70.8% | — |
| OTIS Mock AIME 2024-2025 | 94.2% | — |
| ProofBench | 36% | — |
| GSM8K | — | 36.9% |
Knowledge Gemini 3.6 Flash leads
Gemini 3.6 Flash: 67.8 (#7), Llama 2-13B: 27.5 (#244)
| Benchmark | Gemini 3.6 Flash | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1489 | 1030 |
| GPQA Diamond | 94.1% | — |
| SimpleQA Verified | 66.2% | — |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
Gemini 3.6 Flash: 38.7 (#55), Llama 2-13B: —
| Benchmark | Gemini 3.6 Flash | Llama 2-13B |
|---|---|---|
| LMArena Vision | 1297 | — |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 23.3% | — |
| LMArena Document | 1456 | — |
| ScienceQA | — | 55.8% |
Multilingual Gemini 3.6 Flash leads
Gemini 3.6 Flash: 56.8 (#17), Llama 2-13B: 26.7 (#274)
| Benchmark | Gemini 3.6 Flash | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1470 | 1024 |
| LMArena Chinese | 1530 | 1001 |
| LMArena French | 1501 | 1043 |
| LMArena German | 1478 | 1009 |
| LMArena Japanese | 1477 | 894 |
| LMArena Korean | 1435 | 953 |
| LMArena Russian | 1490 | 1055 |
| LMArena Spanish | 1477 | 1086 |
Instruction Following Gemini 3.6 Flash leads
Gemini 3.6 Flash: 77.2 (#27), Llama 2-13B: 53.5 (#282)
| Benchmark | Gemini 3.6 Flash | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1467 | 1046 |
Long Context Gemini 3.6 Flash leads
Gemini 3.6 Flash: 45.1 (#47), Llama 2-13B: 32.3 (#264)
| Benchmark | Gemini 3.6 Flash | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1475 | 1064 |
Writing & Preference Gemini 3.6 Flash leads
Gemini 3.6 Flash: 68.3 (#26), Llama 2-13B: 30.0 (#284)
| Benchmark | Gemini 3.6 Flash | Llama 2-13B |
|---|---|---|
| LMArena Text | 1478 | 1085 |
| LMArena Creative Writing | 1464 | 1047 |
| LMArena Multi-Turn | 1481 | 1050 |
| EQ-Bench Creative Writing | 1604 | — |
Frequently asked questions
Is Gemini 3.6 Flash better than Llama 2-13B?
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 29.1 on the Noometry Index.
Is Gemini 3.6 Flash or Llama 2-13B better for coding?
Gemini 3.6 Flash scores higher on coding benchmarks: 49.6 versus 30.4 in the Noometry coding category.
How many benchmarks do Gemini 3.6 Flash and Llama 2-13B share?
20 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and Llama 2-13B has 32.