Gemini 1.5 Flash 8B
Gemini 1.5 Flash 8B.
12
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Google DeepMind Oct 2024 Gemini 1.5 Flash 8B
Closed weights
No Epoch Capabilities Index score yet
- GPQA Diamond 33% #203 /229
- CoreCognition 62.9% #11 /119
- RewardBench 2 48.5% #37 /42
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| FACTS Grounding | 79.7% | #12 of 34 | Official leaderboard | |
| RewardBench | 76% | #33 of 48 | Official leaderboard | |
| ECLeKTic | 9.09% | #27 of 35 | Official leaderboard | |
| LMArena (Elo) | 1,259 | #260 of 335 | Official leaderboard | |
| RewardBench 2 | 48.5% | #37 of 42 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.58% | #183 of 212 | Epoch AI run | |
| GPQA Diamond | 33% | #203 of 229 | Epoch AI run | |
| DTBench | 50% | #165 of 180 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LisanBench | 77.0 | #116 of 133 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CoreCognition | 62.9% | #11 of 119 | Official leaderboard | |
| Vibe-Eval | 54.1% | #4 of 5 | Official leaderboard | |
| Vision Arena | 1,071 | #118 of 136 | Official leaderboard |