SShogo Bench

Gemini 3.8 Flash vs GPT-6.1 Terra

GPT-6.1 Terra leads Gemini 3.8 Flash by 12.8 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Gemini 3.8 Flash wins 4 and GPT-6.1 Terra wins 8 of 12 shared benchmarks. Gemini 3.8 Flash is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGemini 3.8 FlashGPT-6.1 Terra
Agentic coding6379
Long-horizon autonomy6474
Knowledge-work agents4756
Computer use4463
Security & context learning5362

Shared benchmarks

BenchmarkGemini 3.8 FlashGPT-6.1 Terra
APEX-Agentsindex64.3%68.3%
Vending-Bench 2index$5,094$9,107
CritPt18.3%28.0%
FrontierMath Tier 422.0%92.7%
FrontierMath Tiers 1-368.4%90.9%
GPQA Diamond95.4%94.3%
MirrorCode38.9%76.7%
OTIS Mock AIME98.9%100.0%
SciCode56.6%55.1%
SimpleBench82.4%72.2%
SimpleQA Verified69.7%57.3%
WeirdML v37.4%28.1%

Specs and price

Gemini 3.8 FlashGPT-6.1 Terra
Agent Index56.2 (#21)69 (#8)
Agent $/M$0.35$0.42
Input / output $/M$0.75 / $3.75$1.00 / $5.00
Context1M1.1M
ReleasedSep 2, 2026Oct 26, 2026
WeightsClosedClosed
API hosts64

Don’t pick one. Route.

Shogo can run Gemini 3.8 Flash and GPT-6.1 Terra side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo