Skip to content

Google · Chat

Gemini 2.5 Pro

Google 🇺🇸ChatGemini familyOne of its sources says the weights aren't publicly available.The maker lists this model as deprecated (20 Oct 2026).
From Netmind's listing:
Gemini 2.5 Pro is the flagship reasoning model from Google for complex, multi-step tasks. It combines advanced thinking, a very long context window, and strong multimodal understanding across text, image, and video, making it well suited for coding, analysis, and agentic workloads.
llminfo IQ
128.8
Max context
1.1M
Listings
73

Evidence and sources

llminfo IQ 128.8, ranked among chat models. From 374 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 100.6, 95% interval 83–118. From 16 benchmark families across 13 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedPoor value (36.3). Costs more per task than its benchmark results predict. From 39 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsTypical (54 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.Median 26,619 output tokens per task at default effort.How the Yap score worksReleased 25 Mar 2025 Training-data cutoff, as its sources state it Maker HQ: US (according to Google's own website)
All rankings: #134 on OpenRouter today #152 on OpenRouter this week #159 on OpenRouter this month #466 on NanoGPT recently #528 on NanoGPT recentlySources: Google Generative AI API data docs, LMArena data, LiteLLM data, Models.dev data, AI/ML API data, OpenRouter data docs, NetMind.AI, llminfo researchPrimary data from Google Generative AI API from LMArena: variant from LiteLLM: deprecation date from Models.dev: weights availability from AI/ML API: primary mode from OpenRouter: knowledge cutoff from NetMind.AI: description from llminfo research: release date
Tags from its sources:instructtoolsvisionreasoningaudio

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Trade-offs

Deprecated by its maker

The maker has already deprecated this model (20 Oct 2026).

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 8 maker's prices; 2 market median prices.

Input & output

as stated by the model's providers
Text
Images
Audio
Video
Files
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingPDF inputWeb searchAudio inputBatch API

Listings

 Googlemodels/gemini-2.5-proSources: GenAI Prices data, Google Generative AI API data docs, LiteLLM data, Models.dev data, Portkey Models data1M$1.25>128k $2.50>200k $2.50cache read $0.125batch $0.625$10.00>128k $15.00>200k $15.00batch $5.00—————
 OpenRouterInference by Googlegoogle/gemini-2.5-pro · flexSource: OpenRouter data docs1M$0.625cache read $0.0625$5.00$0.625$0.0625$0.00000063942,769.5ms
 Vercelgoogle/gemini-2.5-pro-batch · batchSource: Vercel AI Gateway data1M$0.625cache read $0.125$5.00—————
 Poegoogle/gemini-2.5-proSource: Models.dev data1.1M$0.87cache read $0.087$7.00—————
 Meganovagemini/gemini-2.5-proSource: MegaNova data1M$1.00$8.00—————
 Jiekougemini-2.5-proSource: Models.dev data1M$1.1875cache read $0.1187$9.50—————
 302aigemini-2.5-proSources: 302.ai data, Models.dev data1M$1.25$10.00—————
 Aihubmixgemini-2.5-proSource: AIHubMix data docs1M$1.25cache read $0.125$10.00—————
 Atlascloudgoogle/gemini-2.5-proSource: AtlasCloud data1M$1.25cache read $0.125$10.00—————
 Fastroutergoogle/gemini-2.5-proSources: FastRouter data, Models.dev data1M$1.25>200k $2.50cache read $0.125batch $0.625$10.00>200k $15.00batch $5.00—————
Show all 60 listings

Showing 10 of 60: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Abacus, Auriko, Cloudflare AI Gateway, Cortecs AI, Crossmodel, Databricks, DeepInfra, Flowdot, Frogbot, Impossibl, Kilo, Merge Gateway, Modelis, NanoGPT, Netmind, Nous Portal, Oci, Ofox, Orcarouter, Requesty, Sap AI Core, Standardcompute, Vercel AI Gateway, Zenmux.

13 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Human preference

Arena ELO68 related benchmarks · 68 results
Show 62 more resultsHide 62 results
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

Coding

Arena ELOSource: LMArena data · Nov 2026
Multi-SWE-bench10 related benchmarks · 28 results
C Verified
Source: Multi-SWE-bench Experiments data docs · Apr 2025
MagentLess, 20250426_MagentLess_Gemini-2.5-Pro
MopenHands, 20250426_MopenHands_Gemini-2.5-Pro
MSWE-agent, 20250426_MSWE-agent_Gemini-2.5-Pro
C++ Verified
Source: Multi-SWE-bench Experiments data docs · Apr 2025
MagentLess, 20250426_MagentLess_Gemini-2.5-Pro
MopenHands, 20250426_MopenHands_Gemini-2.5-Pro
MSWE-agent, 20250426_MSWE-agent_Gemini-2.5-Pro
Flash All Verified
Source: Multi-SWE-bench Experiments data docs · Jul 2025
MopenHands, 20250712_MopenHands_Gemini-2.5-Pro
Go Verified
Source: Multi-SWE-bench Experiments data docs · Apr 2025
MagentLess, 20250426_MagentLess_Gemini-2.5-Pro
MopenHands, 20250426_MopenHands_Gemini-2.5-Pro
MSWE-agent, 20250426_MSWE-agent_Gemini-2.5-Pro
Java Verified
Source: Multi-SWE-bench Experiments data docs · Apr 2025
MagentLess, 20250426_MagentLess_Gemini-2.5-Pro
MopenHands, 20250426_MopenHands_Gemini-2.5-Pro
MSWE-agent, 20250426_MSWE-agent_Gemini-2.5-Pro
JavaScript Verified
Source: Multi-SWE-bench Experiments data docs · Apr 2025
MagentLess, 20250426_MagentLess_Gemini-2.5-Pro
MopenHands, 20250426_MopenHands_Gemini-2.5-Pro
MSWE-agent, 20250426_MSWE-agent_Gemini-2.5-Pro
Show 12 more resultsHide 12 results
Lite All Verified
Source: Multi-SWE-bench Experiments data docs · Apr 2025
MagentLess, 20250426_MagentLess_Gemini-2.5-Pro
MopenHands, 20250426_MopenHands_Gemini-2.5-Pro
MSWE-agent, 20250426_MSWE-agent_Gemini-2.5-Pro
Python Verified
Source: Multi-SWE-bench Experiments data docs · Apr 2025
MagentLess, 20250426_Agentless_Gemini-2.5-Pro
MopenHands, 20250426_OpenHands_Gemini-2.5-Pro
MSWE-agent, 20250426_SWE-agent_Gemini-2.5-Pro
Rust Verified
Source: Multi-SWE-bench Experiments data docs · Apr 2025
MagentLess, 20250426_MagentLess_Gemini-2.5-Pro
MopenHands, 20250426_MopenHands_Gemini-2.5-Pro
MSWE-agent, 20250426_MSWE-agent_Gemini-2.5-Pro
TypeScript Verified
Source: Multi-SWE-bench Experiments data docs · Apr 2025
MagentLess, 20250426_MagentLess_Gemini-2.5-Pro
MopenHands, 20250426_MopenHands_Gemini-2.5-Pro
MSWE-agent, 20250426_MSWE-agent_Gemini-2.5-Pro
SWE-bench Verified8 related benchmarks · 8 results
SWE-bench Verified
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Show 2 more resultsHide 2 results

Agentic

GAIA4 results
Source: GAIA Leaderboard data · May 2025
Difficulty level
Difficulty not reported
Gaia2Source: Gaia2 (Meta ARE) data · Sep 2025
Source: OpenRouter benchmark exports · Oct 2026
gemini-2.5-pro · 90-day results
Across 2 providers lowest 55% median 57.5% highest 60%OpenRouter's automatic routing 58%
Show results from 2 providers and OpenRouter's automatic routingHide results from 2 providers and OpenRouter's automatic routing
  • Google
  • OpenRouter's automatic routing
  • Google AI Studio

Multilingual

LaoBench20 related benchmarks · 20 results
Show 14 more resultsHide 14 results

Math

Reasoning

MRCRSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Speech

MMARSource: MMAR data

Vision

MMMUSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Vibe-EvalSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Video-MMESource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
VideoMMMUSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

General

Spatialviz BenchSource: Epoch AI Benchmarking Hub data

Long context

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond4 results
Source: Epoch AI Benchmarking Hub data
Setting not stated
Source: OpenRouter benchmark exports · Oct 2026
gemini-2.5-pro · 90-day results
Across 2 providers lowest 82.2% median 82.3% highest 82.4%OpenRouter's automatic routing 82.6%
Show results from 2 providers and OpenRouter's automatic routingHide results from 2 providers and OpenRouter's automatic routing
  • OpenRouter's automatic routing
  • Google
  • Google AI Studio

Factuality

SimpleQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

OCR

OCR ArenaSource: OCR Arena data · Nov 2026

Safety

PhareSource: Phare

Instruction following

Knowledge

Other

ArmBench-LLM Armenian22 related benchmarks · 22 results
Nejumi 428 related benchmarks · 28 results

Data credits: OpenVLM Leaderboard (OpenCompass / VLMEvalKit), Apache-2.0 (licence) · Aider LLM Leaderboards (Aider-AI), Apache-2.0 (licence) · Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · ArmBench-LLM by Metric-AI. Public numeric primary task results; no separate results licence asserted. · ArtifactsBench (Tencent Hunyuan), CC BY 4.0 (licence) · BullshitBench by Peter Gostev, MIT (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Lin et al., CulturALL: Benchmarking Multilingual and Multicultural Competence of LLMs on Grounded Tasks, arXiv:2604.19262v1, CC BY 4.0. Table 2 scores extracted without change. (licence) · DABstep (Adyen), CC BY 4.0 (licence) · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · FaithJudge, Vectara; Tamber et al., EMNLP 2025 Industry. Public numeric README leaderboard; results licence not separately established. · FinSearchComp, CC BY 4.0 (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · Galileo Agent Leaderboard, Apache-2.0 (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · JMLE2026-Bench and IgakuQA119 by Naoto Iwase; results licence not stated (code MIT, question data CC BY 4.0). · LaoBench, BAAI et al., arXiv:2511.11334v3. Cited numeric results only. arXiv non-exclusive distribution notice establishes no results reuse grant; dataset Apache licence is not a results grant. · LiveMCPBench leaderboard, ICIP-CAS (Mo et al., 2025). Sheet linked from the Apache-2.0 project README; sheet licence not separately stated. · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · MathArena (ETH SRI / INSAIT), MIT — cite dekoninck2026matharena (licence) · MineBench, MIT (licence) · MLE-bench (OpenAI), MIT (licence) · Multi-SWE-bench experiments (multi-swe-bench/experiments), Apache-2.0; resolved-rate fractions converted to percentages (licence) · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · Phare (Giskard), CC BY 4.0 (licence) · Shaberi v2.1, Shisa.AI, Apache-2.0. GPT-5.1-judge scores only; judges are not comparable. (licence) · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · SWE-fficiency (swefficiency.com) leaderboard materials, CC BY 4.0; Human Expert reference row omitted (licence) · Sierra Research tau2-bench leaderboard submissions (github.com/sierra-research/tau2-bench), MIT (licence) · UzLiB, Tahrirchi (Abror Shopulatov). Public LEADERBOARD.md numbers; repository MIT covers software and documentation, no separate results licence stated and none asserted. · Vectara Hallucination Leaderboard, Apache-2.0 (licence)

Around the web

Also known as: coding/gemini-2.5-pro, coding/gemini-2.5-pro@europe-central2, coding/gemini-2.5-pro@europe-north1, coding/gemini-2.5-pro@europe-west1, coding/gemini-2.5-pro@europe-west4, coding/gemini-2.5-pro@europe-west8, coding/gemini-2.5-pro@us-central1, coding/gemini-2.5-pro@us-east1, coding/gemini-2.5-pro@us-east5, coding/gemini-2.5-pro@us-south1, coding/gemini-2.5-pro@us-west1, databricks-gemini-2-5-pro, databricks/databricks-gemini-2-5-pro, deepinfra/google/gemini-2.5-pro, gemini-2.5-pro-all, gemini-2.5-pro-grounding, gemini-2.5-pro-preview-06-05, gemini-2.5-pro-preview-06-05-search, gemini-2.5-pro-search, gemini-2.5-pro-thinking, gemini-2.5-pro@eu, gemini/gemini-2.5-pro, google-gemini-2.5-pro, google/gemini-2-5-pro, google/gemini-2.5-pro, google/gemini-2.5-pro-batch, oci/google.gemini-2.5-pro, perplexity/google/gemini-2.5-pro, vercel_ai_gateway/google/gemini-2.5-pro, vertex/gemini-2.5-pro, vertex/gemini-2.5-pro@europe-central2, vertex/gemini-2.5-pro@europe-north1, vertex/gemini-2.5-pro@europe-west1, vertex/gemini-2.5-pro@europe-west4, vertex/gemini-2.5-pro@europe-west8, vertex/gemini-2.5-pro@us-central1, vertex/gemini-2.5-pro@us-east1, vertex/gemini-2.5-pro@us-east5, vertex/gemini-2.5-pro@us-south1, vertex/gemini-2.5-pro@us-west1

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works