ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Gemini 3.1 Pro PreviewvsMAI-Thinking-1

Gemini 3.1 Pro Preview leads 3 of 3 shared benchmarks. Gemini 3.1 Pro Preview has the larger context window (1.0M tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
3 – 0
Gemini 3.1 Pro Preview leads
Cheaper per token
list price, input + output
Larger context
Gemini 3.1 Pro Preview
1.0M tokens
Provider uptime (30d)
100% · —
Google · Microsoft
Gemini 3.1 Pro Preview
Google · released 2026-02-19
textvisionaudio
Context
1.0M
Max out
66K
Input /1M
$2
Output /1M
$12
Cached /1M
$0.2
Scores
10 · 8 core
MAI-Thinking-1
Microsoft · released 2026-08-12
text
Context
256K
Max out
64K
Input /1M
Output /1M
Cached /1M
Scores
15 · 7 core
Quality

Benchmark matrix

BenchmarkGemini 3.1 Pro PreviewMAI-Thinking-1ΔEdge
Reported by both · 3
GPQA Diamond94.3% 84.2% +10.1 ptGemini 3.1 Pro Preview
AIME 202698.3% matharena94.5% +3.8 ptGemini 3.1 Pro Preview
SimpleQA Verified73.5% epoch31% +42.5 ptGemini 3.1 Pro Preview
Only Gemini 3.1 Pro Preview reports · 6
LMArena Elo1480.1 not reported
ARC-AGI-277.1% not reported
FrontierMath Tier 4 v2 (Epoch AI run)26.8% epochnot reported
FrontierMath Tiers 1-3 v2 (Epoch AI run)59.6% epochnot reported
OTIS Mock AIME 2024-2025 (Epoch AI run)95.6% epochnot reported
SWE-Bench Pro54.2% not reported
Only MAI-Thinking-1 reports · 12
SWE-bench Verifiednot reported73.5%
MMLU-Pronot reported85%
AIME 2025not reported97%
AdvancedIFnot reported85%
BFCL v3not reported72%
GraphWalks (<=128K)not reported90%
HMMT February 2026not reported84.9%
IFBenchnot reported69%
LiveCodeBench v6not reported87.7%
MultiChallengenot reported53%
SWE-bench Pronot reported52.8%
Terminal-Bench 2.0not reported46%
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Gemini 3.1 Pro Preview minus MAI-Thinking-1 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecGemini 3.1 Pro PreviewMAI-Thinking-1Edge
Context window1.0M tokens256K tokensGemini 3.1 Pro Preview
Max output66K tokens64K tokensGemini 3.1 Pro Preview
Input price / 1M$2
Output price / 1M$12
Cached input / 1M$0.2
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$14
Modalitiestext · vision · audiotextGemini 3.1 Pro Preview
Released2026-02-192026-08-12
Cited benchmark scores1015
Reliability

Provider status

All providers
More matchups

Gemini 3.1 Pro Preview vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Gemini 3.1 Pro Preview and MAI-Thinking-1 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.