Google DeepMindproprietary
Released: 2026-05-18Gemini 3 Pro
Google DeepMind multimodal frontier model with native video comprehension and 2M token context window.
Intelligence Index
92.5/ 100
Calibrated multi-domain compositeThroughput Speed
80tok/sec
Output streaming throughputTime To First Token
360ms
Initial chunk server latencyLiveBench Contam-Free
79.8%
September 2026 suite scoreLiveBench Multi-Domain Evaluation Breakdown
Monthly refreshed contamination-free test setsLogical Reasoning92.0%
Coding & Repo Repair81.5%
Mathematics (AIME)92.0%
Data Analysis & Tables88.0%
Language & Comprehension89.0%
Instruction Following93.5%
Sourced Benchmark Evaluations (4)
Verified performance across authoritative benchmarks with provenance tracking.| Benchmark | Status | Score | Trust | Date | Source Type | Provenance |
|---|---|---|---|---|---|---|
| ARC-AGI-2 | Nearing Saturation | 71.8% | 75 | 2026-06-15 | independent | Source ↗ |
| SWE-bench Verified | Saturated | 61.9% | 25 | 2026-05-27 | independent | Source ↗ |
| IFEval | Deprecated | 93.5% | 25 | 2026-05-22 | independent | Source ↗ |
| Humanity's Last Exam | Active | 38.3% | 90 | 2024-06-01 | independent | Source ↗ |
OpenAI Compatible API ExecutionAPI Ready
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="gemini-3-pro",
messages=[{"role": "user", "content": "Evaluate multi-step logic problem"}],
temperature=0.2
)
print(response.choices[0].message.content)Evaluation & Sourcing Notes
Scores listed for Gemini 3 Pro represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.
All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.