Skip to main content
BenchLM
Data

Data as of October 17, 2026 · How the score is built

EstablishedProprietaryNon-Reasoning

Released March 20251M context

Gemini 2.5 Pro

Decision readingGemini 2.5 Pro scores 49.1 out of 100 and ranks #102 of 224. This profile shows 9 source-displayable benchmark rows; its strongest eligible category is Knowledge at #96. API pricing is $1.25 input and $10 output per million tokens, with cached input at $0.125.

Released March 2025 — see all recent releases

Find alternativesCompare Gemini 2.5 Pro
Share or export
Share on XLinkedIn
Social cardBenchmarks CSVAPI/MCP query guide

Decision snapshot

Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.

Capability

49.1/100

field median 49.6#102 of 224 ranked models

Public

#102of 224

Verified #60 of 88

Price

$1.25input / $10 output

input median $0.75cached $0.13 · batch + cache $0.13 · blended $5.63

Speed

118tok/s

field median 92 tok/sFirst token 22.41 s

Context

1Mtokens

field median 256,000Maximum output length is tracked separately

Strongest published evidence

Knowledge ranks #96. Particularly effective for knowledge-intensive tasks like research, analysis, and factual Q&A.

Validate before choosing

9 published rows leave some tracked benchmark slots empty. Coding is its lowest eligible category at #115.

Source-linked · 9 displayable benchmark rows

Category score record

Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #102 of 128Percentile 20thWeight 22%1 benchmarkVerified
25.7
CodingRank #115 of 150Percentile 23rdWeight 20%3 benchmarksVerified
22.3
ReasoningWeight 17%0 benchmarksNot measured
Not measured
MultimodalWeight 12%0 benchmarksNot measured
Not measured
KnowledgeRank #96 of 184Percentile 48thWeight 12%2 benchmarksMixed sources
45.6
MultilingualWeight 7%0 benchmarksNot measured
Not measured
Inst. FollowingWeight 5%0 benchmarksNot measured
Not measured
MathRank Not rankedWeight 5%3 benchmarksMixed sources
36.9

9 of 681 tracked benchmark slots have displayable evidence · bars run 0–100

Coverage details

How much of this is verified

Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.

  1. Agentic1/1 verified
  2. Coding3/3 verified
  3. ReasoningNot measured
  4. MultimodalNot measured
  5. Knowledge1/2 verified
  6. MultilingualNot measured
  7. Inst. FollowingNot measured
  8. Math2/3 verified
Verified sourceProvisionalNot measured

Capability shape

Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.

Gemini 2.5 Pro category percentile values

  • Agentic20th percentile
  • Coding23rd percentile
  • ReasoningNot eligible
  • MultimodalNot eligible
  • Knowledge48th percentile
  • MultilingualNot eligible
  • Instruction followingNot eligible
  • MathNot eligible

The dashed outline is median of 6 nearest peers.

Eligible category ranks

  1. Agentic#102/128
  2. Coding#115/150
  3. ReasoningNot ranked
  4. MultimodalNot ranked
  5. Knowledge#96/184
  6. MultilingualNot ranked
  7. Inst. FollowingNot ranked
  8. MathNot ranked
Top decileTop quartileMid-fieldNot eligible

Benchmark ledger

Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.

Coding3 rows
Coding benchmark values, best verified comparison, weight, and source status
SWE-bench VerifiedSoftware Engineering Benchmark VerifiedScore63.8%Versus best verified row

Best verified: Claude Opus 5 · 96%

Gap32.2 behindWeightDisplay only
Provider exact
Google: Gemini 2.5 Pro
Vibe Code BenchVibe Code Bench v1.1Score0.40%Versus best verified row

Best verified: Gemini 4 Argon · 91.90%

Gap91.5 behindWeightDisplay only
Benchmark exact
Vals AI: Vibe Code Bench v1.1
SWE-bench (Vals)SWE-bench, Vals AI runScore54.4%Versus best verified row

Best verified: Claude Opus 5 · 97.0%

Gap42.6 behindWeightDisplay only
Verified
Vals AI: SWE-bench leaderboard
Agentic1 row
Agentic benchmark values, best verified comparison, weight, and source status
Gert LabsGert Labs Composite Game BenchmarkScore42.01%Versus best verified row

Best verified: Claude Opus 4.8 · 72.97%

Gap31 behindWeightDisplay only
Benchmark exact
Gert Labs rankings
Knowledge2 rows
Knowledge benchmark values, best verified comparison, weight, and source status
HLEHumanity's Last ExamScore18.8%Versus best verified row

Best verified: Claude Fable 5.1 · 65%

Gap46.2 behindWeight44% ref. weight
Provider exact
Google: Gemini 2.5 Pro
GPQAGraduate-Level Google-Proof Q&AScore83%Versus best verified row

Best verified: GPT-6 Astra · 96%

Gap13 behindWeight3% ref. weight
Reported
Reported upstream source
Math3 rows
Math benchmark values, best verified comparison, weight, and source status
FrontierMath v2 (Tiers 1-3)FrontierMath v2 Tiers 1-3Score24.561%Versus best verified row

Best verified: GPT-6 Astra · 93.684%

Gap69.1 behindWeightWeighted 30%
Benchmark exact
Epoch AI FrontierMath v2 leaderboard
FrontierMath v2 (Tier 4)FrontierMath v2 Tier 4Score0.000%Versus best verified row

Best verified: GPT-6.1 Sol · 100.000%

Gap100 behindWeightWeighted 10%
Benchmark exact
Epoch AI FrontierMath v2 leaderboard
AIME 2024American Invitational Mathematics Examination 2024Score92%Versus best verified row

Best verified: GPT-OSS 120B · 95.8%

Gap3.8 behindWeightDisplay only
Secondary exact
Phi-4-reasoning-plus model card comparison table

Bars run 0–100; the dark tick marks the best source-verified value

All 9 rows

What it costs to get this score

Published API price against the public score. The x-axis uses a log scale; the dashed path marks models that are not beaten by a cheaper, higher-scoring option. Price uses average of published input and output rates.

Current modelExplore all models

Gemini 2.5 Pro · 49.1 score · $5.63 blended per million tokens

The chart opens on the current model. Scroll horizontally to inspect the full price axis.

405060708090100$0.10$0.50$1$5$10$25$50$100↘ frontierGemini 2.5 Pro

Horizontal: blended price per million tokens, log scale · Vertical: public score

Price vs performance

Published price history

This chart appears only when at least two dated first-party price records exist for the exact model. It shows rate changes, not an inferred cost trend.

06122025-062026-042026-07Output priceInput price

3 dated first-party price records. The newest record lists $10 per million tokens.

Lineage

The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.

  1. March 2025 · you are here

    Gemini 2.5 Pro

    Score 49.1 · $1.25 / $10

Base entry

Spec sheet

Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.

API model ID
gemini-2.5-proGoogle Gemini API pricing
Context window
1MGoogle Gemini API pricing
Maximum output
Not sourced yet
Knowledge cutoff
Not sourced yet
Input modalities
Not sourced yet
Output modalities
Not sourced yet
Parameters
Not disclosed by the provider
Availability
Not sourced yet
Cloud regions
Not tracked yet
Lifecycle
Established
API capabilities
Tool calling, structured outputs, and batch support are not tracked yet
Prompt caching
Published at $0.13 per million cached input tokensGoogle Gemini API pricing
Self-host
Weights are not published
Rate limits
Not tracked yet

How to read this profile

The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.

Gemini 2.5 Pro ranks #102 of 224 on the public leaderboard with a score of 49.14/100. Its source-verified position is #60 of 88.

Gemini 2.5 Pro is a proprietary model with a 1M context window. No explicit reasoning mode is documented in this profile.

9 of 681 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.

Its strongest eligible category is Knowledge at #96, while its lowest eligible position is Coding at #115. particularly effective for knowledge-intensive tasks like research, analysis, and factual Q&A.

Last updated October 17, 2026. Runtime fields remain blank until a sourced snapshot exists.

Questions

How does Gemini 2.5 Pro perform overall in AI benchmarks?

Gemini 2.5 Pro ranks #102 out of 224 models on the public BenchAlign leaderboard, with a score of 49.14/100. Its evidence status is Supported, and this profile shows 9 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.

Is Gemini 2.5 Pro good for knowledge and understanding?

Gemini 2.5 Pro ranks #96 out of 184 eligible models for knowledge and understanding, with a public category score of 45.6/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is Gemini 2.5 Pro good for coding and programming?

Gemini 2.5 Pro ranks #115 out of 150 eligible models for coding and programming, with a public category score of 22.3/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is Gemini 2.5 Pro good for mathematics?

Gemini 2.5 Pro has source-displayable benchmark coverage for mathematics, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is Gemini 2.5 Pro good for agentic tool use and computer tasks?

Gemini 2.5 Pro ranks #102 out of 128 eligible models for agentic tool use and computer tasks, with a public category score of 25.7/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Does Gemini 2.5 Pro have full benchmark coverage on BenchLM?

No. Gemini 2.5 Pro currently has 26 source-displayable rows across 681 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.

What is the context window size of Gemini 2.5 Pro?

Gemini 2.5 Pro has a documented context window of 1M. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.

Watch Gemini 2.5 Pro in the weekly brief

Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.

Read a sample issue

Join 5,600+ readers.

Compare Gemini 2.5 Pro with every tracked model953 comparisons