Gemini 4.0 Benchmarks, Pricing & Rankings
Google · 2026-07-08 · Closed · Current
Snapshot 2026-10-14 · updated weekly
Gemini 4.0 ranks #13 of 42 on the AMR leaderboard.
Gemini 4.0 benchmark scores
| GPQA Diamond | 87.9% | |
| MMLU-Pro | 85.6% | |
| SWE-Bench Verified | 68.4% | |
| AIME 2025 | 87.2% | |
| LiveCodeBench v6 | 75.8% | |
| Arena Elo | 1421 |
Gemini 4.0 price, speed & context
Input price
$2.20
per 1M tokens
Output price
$10
per 1M tokens
Speed
158
tok/s
Context
2M
tokens
About Gemini 4.0
Gemini 4.0 brought the 2M context window to Google’s flagship line and remains the best long-document model per dollar before Argon arrived.
Models around Gemini 4.0 in the rankings
More Google models
Gemini 4.0 FAQ
Where does Gemini 4.0 rank?
Gemini 4.0 ranks #13 of 42 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 89.0. Its strongest dimension is GPQA Diamond at 87.9%.
How much does Gemini 4.0 cost?
Gemini 4.0 costs $2.20 per million input tokens and $10 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $8.05 per million tokens.
What is the Gemini 4.0 context window?
Gemini 4.0 supports a 2M token context window and generates at a median 158 output tokens per second. That context fits roughly 1333 standard documents in a single prompt.
Is Gemini 4.0 open source?
No — Gemini 4.0 is a closed model available only through Google’s official API and authorized cloud partners.
What is better than Gemini 4.0?
GPT-5.6 Sol ranks one place higher at #12 with an AMR score of 89.7. Gemini 4.0 still wins 1 of the tracked dimensions head-to-head — check the comparison table to see exactly which.