Model comparison
Gemini 1.0 Pro vs Llama-3.3-70B-Instruct
Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.6 to 27.3 on the Noometry Index.
Last verified . 22 shared benchmarks.
Google
MetaSummary
- They share 22 benchmarks with published results for both. Gemini 1.0 Pro scores higher in 3 categories and Llama-3.3-70B-Instruct in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama-3.3-70B-Instruct leads 30.6 to 15.6.
- The biggest single-benchmark swing is MATH Level 5: 11.2% for Gemini 1.0 Pro and 41.6% for Llama-3.3-70B-Instruct.
- Llama-3.3-70B-Instruct has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.0 Pro | Llama-3.3-70B-Instruct | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 27.3 | 30.6 |
| Released | 2023-12-13 | 2024-12-06 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.32 |
| Results tracked | 24 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.0 Pro leads
Gemini 1.0 Pro: 32.2 (#275), Llama-3.3-70B-Instruct: 31.0 (#290)
| Benchmark | Gemini 1.0 Pro | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Coding | 1108 | 1268 |
| SciCode | — | 26% |
| WeirdML | — | 14.4% |
| BigCodeBench Instruct | — | 46.9% |
| LiveBench Coding | — | 36.6% |
| BigCodeBench Complete | — | 57.5% |
| HumanEval+ | 55.5% | — |
| MBPP+ | 61.4% | — |
Agentic & Tool Use Not comparable
Gemini 1.0 Pro: —, Llama-3.3-70B-Instruct: 25.8 (#105)
| Benchmark | Gemini 1.0 Pro | Llama-3.3-70B-Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 31.9% |
| BALROG | — | 23% |
Reasoning Gemini 1.0 Pro leads
Gemini 1.0 Pro: 17.1 (#296), Llama-3.3-70B-Instruct: 14.1 (#327)
| Benchmark | Gemini 1.0 Pro | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Hard Prompts | 1109 | 1257 |
| DTBench | 45.9% | 59.5% |
| Epoch Capabilities Index | 117.04 | 127.33 |
| SimpleBench | — | 19.9% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 50.8% |
| LiveBench Data Analysis | — | 49.5% |
| LMCA | — | 17.5% |
| ForecastBench | — | 58.6 |
| LiveBench | — | 50.2% |
Math Llama-3.3-70B-Instruct leads
Gemini 1.0 Pro: 9.3 (#321), Llama-3.3-70B-Instruct: 15.3 (#298)
| Benchmark | Gemini 1.0 Pro | Llama-3.3-70B-Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | 5.1% |
| LMArena Math | 1132 | 1267 |
| MATH Level 5 | 11.2% | 41.6% |
| LiveBench Math | — | 42.2% |
Knowledge Llama-3.3-70B-Instruct leads
Gemini 1.0 Pro: 15.6 (#291), Llama-3.3-70B-Instruct: 30.6 (#226)
| Benchmark | Gemini 1.0 Pro | Llama-3.3-70B-Instruct |
|---|---|---|
| GPQA Diamond | 34% | 47.4% |
| LMArena Expert | 1059 | 1225 |
| MMLU | 70% | 86.3% |
| Confabulations | — | 22.8% |
| Vectara Hallucination Rate | — | 4.1% |
Multilingual Llama-3.3-70B-Instruct leads
Gemini 1.0 Pro: 33.4 (#252), Llama-3.3-70B-Instruct: 39.9 (#220)
| Benchmark | Gemini 1.0 Pro | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Non-English | 1138 | 1236 |
| LMArena Chinese | 1124 | 1217 |
| LMArena French | 1145 | 1281 |
| LMArena German | 1125 | 1251 |
| LMArena Japanese | 1023 | 1150 |
| LMArena Russian | 1186 | 1252 |
| LMArena Spanish | 1119 | 1270 |
| LMArena Korean | — | 1143 |
Instruction Following Llama-3.3-70B-Instruct leads
Gemini 1.0 Pro: 57.6 (#267), Llama-3.3-70B-Instruct: 71.1 (#157)
| Benchmark | Gemini 1.0 Pro | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Instruction Following | 1114 | 1242 |
| LiveBench Instruction Following | — | 82.7% |
Long Context Gemini 1.0 Pro leads
Gemini 1.0 Pro: 34.3 (#249), Llama-3.3-70B-Instruct: 26.4 (#295)
| Benchmark | Gemini 1.0 Pro | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Longer Query | 1132 | 1256 |
| Fiction.LiveBench | — | 33.3% |
Writing & Preference Llama-3.3-70B-Instruct leads
Gemini 1.0 Pro: 36.0 (#264), Llama-3.3-70B-Instruct: 47.6 (#207)
| Benchmark | Gemini 1.0 Pro | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Text | 1149 | 1274 |
| LMArena Creative Writing | 1131 | 1250 |
| LMArena Multi-Turn | 1139 | 1280 |
| LiveBench Language | — | 39.2% |
Frequently asked questions
Is Gemini 1.0 Pro better than Llama-3.3-70B-Instruct?
Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.6 to 27.3 on the Noometry Index.
Is Gemini 1.0 Pro or Llama-3.3-70B-Instruct better for coding?
Gemini 1.0 Pro scores higher on coding benchmarks: 32.2 versus 31.0 in the Noometry coding category.
How many benchmarks do Gemini 1.0 Pro and Llama-3.3-70B-Instruct share?
22 benchmarks have published results for both models. Gemini 1.0 Pro has 24 scored results on Noometry and Llama-3.3-70B-Instruct has 43.