Gemini 2.5 Pro: benchmark labels distinguish AIME 2025 and LiveCodeBench v6

The OnAirToday AI Progress Tracker recorded a verified change to Google DeepMind's Gemini 2.5 Pro (version gemini-2.5-pro): Benchmark labels distinguish AIME 2025 and LiveCodeBench v6.

Gemini 2.5 Pro is Google DeepMind's multimodal reasoning model, with published strengths in coding, mathematics, scientific reasoning and long-context analysis. Its documented configuration accepts text, images, audio and video and produces text, with thinking tokens contributing to output billing.

What changed in this review:

• Historical evaluation results do not establish current leaderboard standings.
• Current availability, retirement status and subsequent pricing changes: Not yet confirmed by public reporting.
• Capability score 64 → 72
• Flaws and limitations updated
• Risks and threats updated

Teams building on Gemini 2.5 Pro 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-pro.

References:

• https://arxiv.org/abs/2507.06261
• https://ai.google.dev/gemini-api/docs/models#gemini-2.5-pro
• https://ai.google.dev/gemini-api/docs/pricing
• https://blog.google/technology/google-deepmind/gemini-2-5-model-family-expands/