Gemini 1.0 Pro
Zero-eval
#1BIG-Bench
by Google
+
+
+
+
About
Gemini 1.0 Pro is a language model developed by Google. The model shows competitive results across 9 benchmarks. Notable strengths include BIG-Bench (75.0%), MMLU (71.8%), WMT23 (71.7%). The model is available through 1 API provider. Released in 2024, it represents Google's latest advancement in AI technology.
+
+
+
+
Pricing Range
Input (per 1M)$0.50 -$0.50
Output (per 1M)$1.50 -$1.50
Providers1
+
+
+
+
Timeline
AnnouncedFeb 15, 2024
ReleasedFeb 15, 2024
Knowledge CutoffFeb 1, 2024
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown
Overall Performance
9 benchmarks
Average Score
48.4%
Best Score
75.0%
High Performers (80%+)
0Performance Metrics
Max Context Window
41.0KAvg Throughput
120.0 tok/sAvg Latency
0ms+
+
+
+
All Benchmark Results for Gemini 1.0 Pro
Complete list of benchmark scores with detailed information
| BIG-Bench | text | 0.75 | 75.0% | Unverified | |
| MMLU | text | 0.72 | 71.8% | Self-reported | |
| WMT23 | text | 0.72 | 71.7% | Unverified | |
| EgoSchema | video | 0.56 | 55.7% | Self-reported | |
| MMMU | multimodal | 0.48 | 47.9% | Unverified | |
| MathVista | multimodal | 0.47 | 46.6% | Unverified | |
| MATH | text | 0.33 | 32.6% | Unverified | |
| GPQA | text | 0.28 | 27.9% | Unverified | |
| FLEURS | audio | 0.06 | 6.4% | Unverified |