Gemini 2.5 Flash: aIME benchmark naming specifies the 2025 competition
Tracker verifies the benchmark’s 2025 competition reference against Google DeepMind documentation
AIME benchmark naming specifies the 2025 competition — verified by the OnAirToday AI Progress Tracker against Google DeepMind's published documentation.
OnAirToday
Newsroom
The OnAirToday AI Progress Tracker recorded a verified change to Google DeepMind's Gemini 2.5 Flash (version gemini-2.5-flash): AIME benchmark naming specifies the 2025 competition.
Gemini 2.5 Flash is Google's general-purpose multimodal model combining configurable reasoning with a focus on price and latency. Its documented specification supports approximately one million input tokens, text output, and integration with tools and external information sources.
What changed in this review:
- Terminal-Bench, FrontierMath and LMArena Text scores: Not yet confirmed by public reporting.
- Capability score 52 → 78
- Flaws and limitations updated
- Risks and threats updated
Teams building on Gemini 2.5 Flash should confirm limits, pricing and benchmark coverage against the vendor's own documentation before relying on these figures.
The full profile — capabilities, benchmark citations, known flaws and risk guidance — is on the tracker at /ai-models/gemini-2-5-flash.
References:
- https://ai.google.dev/gemini-api/docs/models
- https://ai.google.dev/gemini-api/docs/pricing
- https://arxiv.org/abs/2507.06261
- https://blog.google/technology/google-deepmind/gemini-2-5-model-family-expands/
Generated insight by OnAirToday AI
Specifying the 2025 competition clarifies which AIME benchmark the reference denotes. Verification against Google DeepMind documentation gives readers a source for checking that naming.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.