Frontier BenchSI model benchmarks · Jul 2026
ModelsCompareLabsMethodology
All models
GD

Gemini 3.5 Flash

Google DeepMind

Beats the prior Pro flagship on coding at 4× the speed. Volume-pipeline darling.

Fast / CheapProprietary1M contextReleased May 2026textvisionaudio-inaudio-outvideocode

API price · per 1M tokens

$1.5/$9

input / output

≈ $3.38/M blended

Benchmarks

Bar shows this model's score; tick shows the best score across all tracked models for context.

SWE-bench VerifiedReal GitHub issues, human-verified patches. The standard coding-agent benchmark.
79.0/ best 90.1
SWE-bench Pro2,294 harder real-world GitHub issues. Where the frontier separates now.
58.0/ best 69.2
Terminal-Bench 2.xAgentic command-line workflows — planning, iteration, tool coordination.
76.2/ best 84.0
GPQA DiamondGoogle-proof graduate-level science Q&A. General reasoning proxy.
91.0/ best 94.4
MMLU-ProMulti-task language understanding across 120+ academic subjects.
85.0/ best 93.0
HumanEval+Functional code generation from docstrings.
91.0/ best 96.0
MATH-500Competition-style math problems.
89.0/ best 97.8
Humanity's Last ExamHardest reasoning benchmark (with tools). ~50% = near frontier.
49.0/ best 57.9

Other Google DeepMind models

GD

Gemini 3.1 Pro

Frontier

≈$4.50/M

Built by GLM-5.2 · Scores are directional, drawn from public mid-2026 benchmarks.

SWE-bench, GPQA, MMLU, AIME, HLE etc. are trademarks of their respective owners.