Data points: 109
Model compare
Gemini 2.5 Pro vs Gemini 3 Pro
The readout for Gemini 2.5 Pro and Gemini 3 Pro, before the detailed comparison sheet.
Key Takeaways
Weighted outcome: Gemini 3 Pro. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Decision read
Gemini 3 Pro
Gemini 3 Pro has the higher weighted result; Model A / B score 27.3 to 72.7.
Evidence depth
109 data points
Includes 26 benchmark rows, 0 audit samples, and 10 provider examples.
Selection signal
Start with Gemini 3 Pro
The charts below split 36 high-signal samples across speed, scores, and audit health.
Change comparison
Switch either side of this report to compare another model with the same LMSpeed data pipeline.
Select a different model to open a new comparison URL.
Comparison sheet
This report only uses LMSpeed data for Gemini 2.5 Pro and Gemini 3 Pro: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | Gemini 2.5 Pro | Gemini 3 Pro |
|---|---|---|
| Overall leader | Contender | Leading |
| Weighted overall score | 27.3 pts | 72.7 pts |
| Benchmark category leads | 1 categories | 5 categories |
| Operational advantages | Cheapest input price, Average speed, Provider coverage | First-token latency |
| Context window | 1.0M tokens | No data |
| Max output | 65.5K tokens | No data |
| Modalities | Input TextImageFileAudiovideo Output Text | No data |
| Features | Text inputImage inputFile inputAudio inputText outputTool callingStructured outputsJSON modeReasoning | None listed |
The overall result weights benchmark capability categories at 80% and price, API speed/latency, and availability at 20%. Recent test volume does not affect the winner, and missing benchmark categories are excluded.
Model metadata
Model metadata
| Model compare | Gemini 2.5 Pro | Gemini 3 Pro |
|---|---|---|
| Developer | ||
| Released | Jun 2025 | No data |
| Parameters | No data | No data |
| Tokenizer | Gemini | No data |
| Knowledge cutoff | 2025-01-31 | No data |
| OpenRouter ID | google/gemini-2.5-pro | No data |
| References | No data | No data |
When to choose each model
This report only uses LMSpeed data for Gemini 2.5 Pro and Gemini 3 Pro: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
Gemini 2.5 Pro
Gemini 2.5 Pro is stronger in benchmark categories (Math) and operational dimensions (Cheapest input price, Average speed, Provider coverage).
Gemini 3 Pro
Gemini 3 Pro is stronger in benchmark categories (Agents, Coding, Reasoning, Knowledge, Instruction following) and operational dimensions (First-token latency).
Benchmark score comparison
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
Category performance
Compare benchmark category scores on a 0-100 scale. Select a category to inspect the gap.
- Model A coverage
- 6 / 8
- Model B coverage
- 8 / 8
- Shared
- 6 shared categories
Avg. score
Gemini 2.5 Pro
45.7
Avg. score
Gemini 3 Pro
52.8
Agents
Gemini 3 Pro leads by 5.4
Coding
Gemini 3 Pro leads by 15.9
Reasoning
Gemini 3 Pro leads by 0.1
Knowledge
Gemini 3 Pro leads by 22.9
Math
Gemini 2.5 Pro leads by 1.0
Multilingual
Gemini 3 Pro
Multimodal
Gemini 3 Pro
Instruction following
Gemini 3 Pro leads by 6.7
Professional benchmark details
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
Professional benchmark details
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
Gemini 2.5 Pro
43.0
Rank #104/112 · confidence 1 · eval date 2025-03-01
Gemini 3 Pro
winner61.0
Rank #43/112 · confidence 3 · eval date 2025-11-18
Gemini 2.5 Pro
winner$1.25/M
Rank #123/186 · confidence 4
Gemini 3 Pro
$2.00/M
Rank #143/186 · confidence 4
Gemini 2.5 Pro
winner$3.44/M
Rank #139/186 · confidence 4
Gemini 3 Pro
$4.50/M
Rank #152/186 · confidence 4
Gemini 2.5 Pro
winner$10.00/M
Rank #142/186 · confidence 4
Gemini 3 Pro
$12.00/M
Rank #152/186 · confidence 4
Gemini 2.5 Pro
86.2%
Rank #18/129 · confidence 4
Gemini 3 Pro
winner89.5%
Rank #2/129 · confidence 4
Gemini 2.5 Pro
2.6
Rank #58/88 · confidence 1 · eval date 2025-03-01
Gemini 3 Pro
winner9.1
Rank #36/88 · confidence 3 · eval date 2025-11-18
Gemini 2.5 Pro
66.0
Rank #74/106 · confidence 1 · eval date 2025-03-01
Gemini 3 Pro
winner76.0
Rank #46/106 · confidence 3 · eval date 2025-11-18
Gemini 2.5 Pro
84.4%
Rank #71/218 · confidence 4
Gemini 3 Pro
winner88.7%
Rank #47/218 · confidence 4
Gemini 2.5 Pro
22.5%
Rank #77/216 · confidence 4
Gemini 3 Pro
winner29.5%
Rank #58/216 · confidence 4
Gemini 2.5 Pro
80.1%
Rank #18/115 · confidence 4
Gemini 3 Pro
winner85.7%
Rank #7/115 · confidence 4
Gemini 2.5 Pro
42.8
Rank #61/113 · confidence 1 · eval date 2025-03-01
Gemini 3 Pro
winner56.1
Rank #15/113 · confidence 3 · eval date 2025-11-18
Gemini 2.5 Pro
38.7
Rank #76/87 · confidence 1 · eval date 2025-03-01
Gemini 3 Pro
winner61.6
Rank #23/87 · confidence 3 · eval date 2025-11-18
Gemini 2.5 Pro
0.4
Rank #33/33 · confidence 1 · eval date 2025-03-01
Gemini 3 Pro
winner14.3
Rank #26/33 · confidence 3 · eval date 2025-11-18
Gemini 2.5 Pro
4.2
Rank #24/36 · confidence 1 · eval date 2025-03-01
Gemini 3 Pro
winner18.8
Rank #13/36 · confidence 3 · eval date 2025-11-18
Gemini 2.5 Pro
14.1
Rank #32/47 · confidence 1 · eval date 2025-03-01
Gemini 3 Pro
winner37.6
Rank #14/47 · confidence 3 · eval date 2025-11-18
Gemini 2.5 Pro
35.3
Rank #47/63 · confidence 1 · eval date 2025-03-01
Gemini 3 Pro
winner55.4
Rank #33/63 · confidence 3 · eval date 2025-11-18
Gemini 2.5 Pro
39.1
Rank #39/106 · confidence 1 · eval date 2025-03-01
Gemini 3 Pro
winner55.8
Rank #7/106 · confidence 3 · eval date 2025-11-18
Gemini 2.5 Pro
23.5
Rank #83/83 · confidence 1 · eval date 2025-03-01
Gemini 3 Pro
winner82.5
Rank #10/83 · confidence 3 · eval date 2025-11-18
Gemini 2.5 Pro
90.9
Rank #16/106 · confidence 1 · eval date 2025-03-01
Gemini 3 Pro
winner91.5
Rank #15/106 · confidence 3 · eval date 2025-11-18
Gemini 2.5 Pro
84.4
Rank #63/113 · confidence 1 · eval date 2025-03-01
Gemini 3 Pro
winner90.8
Rank #28/113 · confidence 3 · eval date 2025-11-18
Gemini 2.5 Pro
22.5
Rank #65/114 · confidence 1 · eval date 2025-03-01
Gemini 3 Pro
winner39.7
Rank #29/114 · confidence 3 · eval date 2025-11-18
Gemini 2.5 Pro
25.9
Rank #61/117 · confidence 1 · eval date 2025-03-01
Gemini 3 Pro
winner28.0
Rank #53/117 · confidence 3 · eval date 2025-11-18
Gemini 2.5 Pro
74.9
Rank #36/68 · confidence 1 · eval date 2025-03-01
Gemini 3 Pro
winner80.2
Rank #14/68 · confidence 3 · eval date 2025-11-18
Gemini 2.5 Pro
48.7
Rank #57/84 · confidence 1 · eval date 2025-03-01
Gemini 3 Pro
winner70.4
Rank #33/84 · confidence 3 · eval date 2025-11-18
Gemini 2.5 Pro
42.0
Rank #33/49 · confidence 1 · eval date 2025-03-01
Gemini 3 Pro
winner63.2
Rank #7/49 · confidence 3 · eval date 2025-11-18
Gemini 2.5 Pro
54.1
Rank #64/82 · confidence 1 · eval date 2025-03-01
Gemini 3 Pro
winner87.1
Rank #38/82 · confidence 3 · eval date 2025-11-18
API audit comparison
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
API audit comparison
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | Gemini 2.5 Pro | Gemini 3 Pro |
|---|---|---|
| No completed audits are available from shared providers yet. | ||
Provider examples
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
Provider examples
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | Gemini 2.5 Pro | Gemini 3 Pro |
|---|---|---|
CatClaw API30 tests | Gemini 2.5 Pro speed / latency 48 tok/s / 23637ms input / output No data | Gemini 3 Pro speed / latency N/A / N/A input / output No data |
N1N20 tests | Gemini 2.5 Pro speed / latency 106 tok/s / 16405ms input / output No data | Gemini 3 Pro speed / latency 83 tok/s / 14822ms input / output No data |
Rnglg2 API10 tests | Gemini 2.5 Pro speed / latency 111 tok/s / 17899ms input / output No data | Gemini 3 Pro speed / latency 85 tok/s / 12067ms input / output No data |
DeepRouter5 tests | Gemini 2.5 Pro speed / latency 92 tok/s / 16347ms input / output No data | Gemini 3 Pro speed / latency N/A / N/A input / output No data |
Hi API5 tests | Gemini 2.5 Pro speed / latency N/A / N/A input / output No data | Gemini 3 Pro speed / latency 107 tok/s / 15729ms input / output No data |
Gemini 2.5 Pro gemini-2.5-pro-preview-03-25 speed / latency No data input / output $0/request | Gemini 3 Pro gemini-3-pro-preview-high speed / latency No data input / output $0/request | |
Gemini 2.5 Pro google/gemini-2.5-pro-preview speed / latency No data input / output $0.000001/request | Gemini 3 Pro gemini-3-pro-high speed / latency No data input / output $2.00/M/$12.00/M | |
Gemini 2.5 Pro gemini-2.5-pro-c speed / latency No data input / output $0.0010/request | Gemini 3 Pro gemini-3-pro-preview speed / latency No data input / output $0.411/M/$2.47/M | |
Gemini 2.5 Pro gemini-2.5-pro speed / latency No data input / output $0.086/M/$0.685/M | Gemini 3 Pro gemini-3-pro-preview speed / latency No data input / output $0.0024/request | |
Gemini 2.5 Pro gemini-2.5-pro speed / latency No data input / output $0.0052/request | Gemini 3 Pro gemini-3-pro-preview speed / latency No data input / output $0.0052/request |
FAQ
Weighted outcome: Gemini 3 Pro. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
- Why is this comparison indexable?
- It has 6 verifiable comparison points, and both models have pricing or benchmark data.
- Are missing metrics invented?
- No. Metrics without LMSpeed data are omitted from this report.