LIVE INTELLIGENCE · part of the Xentir AI Index

Gemini 2.5 Pro (Jun 2025, Preview 06 05) vs Kimi K2 Thinking (Turbo)

Name: Gemini 2.5 Pro (Jun 2025, Preview 06 05) vs Kimi K2 Thinking (Turbo) — benchmark results
Creator: Epoch AI
License: https://creativecommons.org/licenses/by/4.0/

Gemini 2.5 Pro (Jun 2025, Preview 06 05) · Google DeepMind, released 2025-06-05
Kimi K2 Thinking (Turbo) OPEN WEIGHTS · Moonshot, released 2025-11-06

“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-09-09 · Methodology · Data Sources

Neither model leads on more of the 2 benchmarks where both are measured — Gemini 2.5 Pro (Jun 2025, Preview 06 05) on 1, Kimi K2 Thinking (Turbo) on 1. The remaining 7 of 9 tracked benchmarks cannot be compared: 4 have a result for only one of the two models, 3 for neither. Nothing on this page is estimated to fill those in.

Head-to-head

Measured on 2 of 9 tracked benchmarks for both models — Gemini 2.5 Pro (Jun 2025, Preview 06 05) leads on 1, Kimi K2 Thinking (Turbo) leads on 1.

Benchmark	Gemini 2.5 Pro (Jun 2025, Preview 06 05)	Kimi K2 Thinking (Turbo)	Leads
Epoch Capabilities Index (ECI)	145.3	145.8	Kimi K2 Thinking (Turbo)
SWE-bench Verified	Not measured	Not measured	Not measured on both
GPQA Diamond	0.848	0.842	Gemini 2.5 Pro (Jun 2025, Preview 06 05)
MATH Level 5	Not measured	Not measured	Not measured on both
OTIS Mock AIME 2024-2025	Not measured	0.831	Comparison unavailable — Gemini 2.5 Pro (Jun 2025, Preview 06 05) has no published result
FrontierMath	0.103	Not measured	Comparison unavailable — Kimi K2 Thinking (Turbo) has no published result
FrontierMath Tier 4	0.021	Not measured	Comparison unavailable — Kimi K2 Thinking (Turbo) has no published result
SimpleQA Verified	Not measured	Not measured	Not measured on both
Chess Puzzles	Not measured	0.200	Comparison unavailable — Gemini 2.5 Pro (Jun 2025, Preview 06 05) has no published result

Benchmark results measure specific tasks and should not be treated as a universal measure of model quality. A model with no row here for a benchmark has not been measured on it — that is left blank, never estimated.

What remains uncertain

Gemini 2.5 Pro (Jun 2025, Preview 06 05) has no published result on Chess Puzzles, OTIS Mock AIME 2024-2025.
Kimi K2 Thinking (Turbo) has no published result on FrontierMath, FrontierMath Tier 4.
3 tracked benchmarks have no published result for either model.

A missing result means Xentir has not found one published by the source it cites, not that the model performs badly. See Data Sources.

Full profiles

Gemini 2.5 Pro (Jun 2025, Preview 06 05) → · Kimi K2 Thinking (Turbo) → · the full AI Model Rankings table