Gemini 2.5 Pro Preview 0605
Note: This preview is mapped to Gemini 2.5 Pro (stable).
- Reasoning
- Vision
- Audio Input
Added Jun 5, 2025
Pricing
Auto routing · per 1M tokens- Input
- $2.50
- Output
- $10.00
- Cache read
- $0.25
Specifications
- Context window
- 1M
- Max output
- 65.5K
Benchmarks
Benchmarks
Sourced from LMArena.
Arena Score
1445.5
Overall Rank
#89 / 421
Votes
124,789
Confidence Interval
1443.0 - 1448.0
Category Scores
Coding
#137 / 416
26,808 votes
1464.2
Math
#98 / 404
7,763 votes
1439.2
Longer Query
#82 / 399
33,799 votes
1456.7
Creative Writing
#54 / 419
17,581 votes
1443.4
Instruction Following
#83 / 421
35,039 votes
1438.1
Hard Prompts
#106 / 421
65,589 votes
1458.2
Additional Categories22
German
#46 / 320
2,646 votes
1470.7
Japanese
#48 / 288
2,059 votes
1443.5
Industry Legal And Government
#60 / 393
8,892 votes
1470.5
Industry Writing And Literature And Language
#67 / 420
28,106 votes
1444.9
Korean
#69 / 289
2,479 votes
1414.1
Industry Entertainment And Sports And Media
#71 / 419
23,184 votes
1430.6
Polish
#71 / 244
6,489 votes
1456.4
Spanish
#71 / 303
3,431 votes
1453.6
Russian
#75 / 385
12,157 votes
1452.0
Industry Life And Physical And Social Science
#76 / 419
20,768 votes
1471.8
Industry Medicine And Healthcare
#80 / 390
7,940 votes
1469.3
Non English
#82 / 421
70,940 votes
1437.1
Chinese
#83 / 395
9,243 votes
1486.6
French
#85 / 301
2,370 votes
1466.7
Exclude Ties
#90 / 421
91,071 votes
1445.2
Multi Turn
#96 / 419
21,115 votes
1447.8
Industry Mathematical
#98 / 401
6,853 votes
1446.8
English
#100 / 421
53,793 votes
1448.8
Expert
#112 / 371
8,242 votes
1458.5
Industry Business And Management And Financial Operations
#112 / 414
22,749 votes
1437.4
Hard Prompts English
#117 / 419
28,813 votes
1457.9
Industry Software And It Services
#129 / 421
43,814 votes
1459.4
Published 2026-11-09 · Matched as Gemini 2.5 Pro · CC BY 4.0
LMArena DatasetLeaderboard results
| Benchmark | Score | Rank on NanoGPT |
|---|---|---|
Epoch AI Benchmarking Hub Epoch AI data, CC BY 4.0 · Updated Nov 12, 2026 | ||
FrontierMath v2 (Tiers 1–3) Tested as Gemini 2.5 Pro | 24.6% | #71 of 83 |
SWE-bench Verified Tested as Gemini 2.5 Pro | 57.6% | #26 of 28 |
GPQA Diamond Tested as Gemini 2.5 Pro | 85.3% | #68 of 119 |
FrontierMath v2 (Tier 4) Tested as Gemini 2.5 Pro | 0.0% | #66 of 67 |
OTIS Mock AIME 2024–2025 Tested as Gemini 2.5 Pro | 84.2% | #78 of 121 |
Sierra τ-bench tau2-bench data, MIT · Updated Aug 4, 2026 | ||
τ³-Banking Tested as Gemini 2.5 Pro | 13.7% | #18 of 18 |
Creative Writing v3 | 1422 | #64 of 96 |
Longform Writing | 53.6 | #67 of 97 |
EQ-Bench 3 | 1523 | #17 of 49 |
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026 | ||
UGI Score Tested as Gemini 2.5 Pro | 47.8 | #49 of 149 |
UGI Willingness Tested as Gemini 2.5 Pro | 2.2 | #102 of 149 |
UGI Writing Tested as Gemini 2.5 Pro | 65.2 | #24 of 149 |
Filtered and ranked to models on NanoGPT.
Providers
Provider information for this model’s automatic routing. These routes cannot be selected individually.
Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)
| Cache write /M | ||||||
|---|---|---|---|---|---|---|
 Recommended | $1.25 | $10.00 | $0.125 | $0.375 | N/A | N/A |
| >200k | $2.50 | $15.00 | $0.25 | N/A | ||
| $1.25 | $10.00 | $0.125 | $0.375 | N/A | N/A | |
| >200k | $2.50 | $15.00 | $0.25 | N/A |
