Across 13 comparable benchmarks, Gemini 3.0 Flash has better reported results on 12 and worse on 0, with 1 tied.
Moderate evidence13 of 13 shared results countedHow we compare
Gemini 2.5 Pro Experimental 03-25 is no longer available through its official API. API prices for this version are not shown.
Price basis: Standard rates vs listed rates. The price section below shows the applicable periods.
| Fact | Gemini 3.0 Flash | Gemini 2.5 Pro Experimental 03-25 |
|---|---|---|
| Context window | 1M tokens | 1M tokens |
| Input / 1M | $0.500 | — |
| Output / 1M | $3.00 | — |
| Blended (4:1) | $0.676 | — |
| Status | Preview | Retired |
| Released | December 17, 2025 | March 25, 2025 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 9 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Gemini 3.0 Flash ahead on 2 of 2 counted
Gemini 3.0 Flash ahead on 2 of 2 counted
Gemini 3.0 Flash ahead on 1 of 2 counted
Gemini 3.0 Flash ahead on 1 of 1 counted
Gemini 3.0 Flash ahead on 2 of 2 counted
Gemini 3.0 Flash ahead on 2 of 2 counted
No shared comparable results for Research & search, Long context, Professional work & productivity, Cybersecurity.
Published scores, with matching modes where available. Gaps show Gemini 3.0 Flash relative to Gemini 2.5 Pro Experimental 03-25. Reading the results
| Benchmark | Gemini 3.0 Flash | Gemini 2.5 Pro Experimental 03-25 | Gap |
|---|---|---|---|
| LiveCodeBenchAlgorithmic Coding · Pass @K | 90.8Thinking · no tools | 70.4≠Normal · no tools | 1.29×#7 vs #55 of 113 |
| SWE-bench VerifiedRepository Engineering · Accuracy | 75.8Thinking High · tools | 63.8≠Normal · no tools | +12.0 pts#35 vs #75 of 108 |
| BALROGLogical Planning · Average progress (%) | 48.1Normal · tools | 43.3Normal · tools | +4.8 pts#7 vs #11 of 31 |
| SimpleBenchCommonsense · Score (AVG@5) | 61.1Normal · no tools | 51.6Normal · no tools | 1.18×#43 vs #63 of 106 |
| AIME2025Mathematics · Accuracy | 99.7Thinking · tools | 86.9≠Normal · no tools | +12.8 pts#8 vs #43 of 86 |
| FrontierMath - Tier 4Mathematics · Accuracy | 4.2Normal · no tools | 4.2Normal · no tools | =#21 vs #21 of 50 |
| GPQA DiamondScientific Reasoning · Accuracy | 90.4Thinking · no tools | 84.0≠Normal · no tools | +6.4 pts#48 vs #88 of 200 |
| Claw BenchTool Orchestration · Accuracy | 85.7Thinking · tools | 80.4Thinking · tools | +5.3 pts#15 vs #20 of 29 |
| Pinch BenchTool Orchestration · Accuracy | 85.2Thinking · tools | 71.9Thinking · tools | +13.3 pts#17 vs #30 of 38 |
| GeoBench ACWVisual Understanding · ACW country accuracy (%) | 88.0Normal · no tools | 81.0≠Normal · tools + web | +7.0 pts#2 vs #10 of 32 |
| VPCTVisual Understanding · Accuracy (%) | 72.6Normal · no tools | 48.0Normal · no tools | +24.6 pts#3 vs #8 of 26 |
| Reported separately from the capability domains; not included in the averages. Read each metric’s direction — lower can be better. | |||
| SimpleQAHonesty & Factuality · Accuracy | 68.7Thinking · no tools | 52.9≠Normal · no tools | +15.8 pts#8 vs #12 of 46 |
| HLEKnowledge Exams · Accuracy | 43.5Thinking · tools | 18.8≠Normal · no tools | +24.7 pts#71 vs #108 of 151 |
Algorithmic Coding · Pass @K
Repository Engineering · Accuracy
Logical Planning · Average progress (%)
Commonsense · Score (AVG@5)
Mathematics · Accuracy
Mathematics · Accuracy
Scientific Reasoning · Accuracy
Tool Orchestration · Accuracy
Tool Orchestration · Accuracy
Visual Understanding · ACW country accuracy (%)
Visual Understanding · Accuracy (%)
Honesty & Factuality · Accuracy
Knowledge Exams · Accuracy
A dash means no result is available.
| Benchmark | Gemini 3.0 Flash | Gemini 2.5 Pro Experimental 03-25 |
|---|---|---|
| AIME 2024 | — | 92.0 |
| AIME 2026 | 96.7 | — |
| CritPt | 8.6 | — |
| FrontierMath Tier 4 v2 | 17.1 | — |
| FrontierMath v2 | 51.2 | — |
| MMLU-Pro | 89.0 | — |
| Aider-Polyglot | — | 72.9 |
| Code Migration | 6.4 | — |
| GSO | 9.8 | — |
| SWE-bench Multilingual | 72.7 | — |
| SWE-Bench Pro - Public | 49.6 | — |
| Terminal Bench 2.0 | 47.6 | — |
| Terminal Bench Hard | 38.6 | — |
| Terminal-Bench 2.1 | 58.0 | — |
| Vibe Code Bench v1.1 | 20.2 | — |
| WeirdML v2 | 61.6 | — |
| MCP-Atlas | 62.0 | — |
| PinchBench v2 | 72.1 | — |
| ECI | 152 | — |
| LiveBench | 72.4 | — |
| Text Arena (Coding) | 1454 | — |
| Creative Writing | — | 1396 |
| IF Bench | 78.0 | — |
| Fiction.liveBench | — | 66.7 |
| MMMU-Pro | 79.9 | — |
| EMB (Excel Modeling) | 26.0 | — |
| Finance Agent v2 | 42.5 | — |
| Harvey's Legal Agent Benchmark | 0.0 | — |
| Legal Research Bench | 18.3 | — |
| SAGE | 51.9 | — |
| Tax Agent Bench | 11.8 | — |
| τ²-Bench | 90.2 | — |
| τ²-Bench - Telecom | 91.2 | — |
| τ³-Banking | 27.3 | — |
| ARC-AGI-1 | 84.7 | — |
| ARC-AGI-2 | 33.6 | — |
| MedCode | 55.9 | — |
| MedScribe | 69.9 | — |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
A blended cost needs a published input and output price on both sides, and one of these two does not have them yet.
Gemini 3.0 Flash: Standard pricing. Google Gemini API official pricing (ai.google.dev/gemini-api/docs/pricing) verified 2026-11-13; paid tier; standard tier; text input Google Gemini API official pricing (ai.google.dev/gemini-api/docs/pricing) verified 2026-11-13; paid tier; standard tier; output
Gemini 2.5 Pro Experimental 03-25: Listed text rates; pricing tier not confirmed.
| Price / 1M tokens | Gemini 3.0 Flash | Gemini 2.5 Pro Experimental 03-25 | Ratio |
|---|---|---|---|
| Input | $0.50 | — | — |
| Output | $3.00 | — | — |
| Cached input | $0.05 | — | — |
| Cache write | — | — | — |
| Blended | $0.676 | — | — |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
| Benchmark | Gemini 3.0 Flash | Gemini 2.5 Pro Experimental 03-25 |
|---|---|---|
| AIME 2026 | Not reported | |
| ARC-AGI-1 | Not reported | |
| ARC-AGI-2 | Not reported | |
| Code Migration | Not reported | |
| EMB (Excel Modeling) | Not reported | |
| Finance Agent v2 | Not reported | |
| Legal Research Bench | Not reported | |
| MedCode | Not reported | |
| MedScribe | Not reported | |
| SAGE | Not reported | |
| Tax Agent Bench | $0.1007 / task Average · Accuracy (%, rubric × citation quality): 11.8 Thinking High (With Tools) | Not reported |
| Vibe Code Bench v1.1 | Not reported |
| Attribute | Gemini 3.0 Flash | Gemini 2.5 Pro Experimental 03-25 |
|---|---|---|
| Availability | Preview | Retired |
| Provider | Google Deep Mind | Google Deep Mind |
| Model type | Chat model | Reasoning model |
| First release | December 17, 2025 | March 25, 2025 |
| Context window | 1M tokens | 1M tokens |
| Max output | 64K tokens | 64K tokens |
| Architecture | Undisclosed | Undisclosed |
| Documented capabilities | Reasoning, Multilingual | Reasoning, Multilingual |
| Input modalities | Text, Image, Audio, Video | Text, Image, Audio, Video |
| Output modalities | Text | Text |
| Weights | Closed / API only | Closed / API only |
| Commercial use | Proprietary | Proprietary |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used Gemini 3.0 Flash or Gemini 2.5 Pro Experimental 03-25? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.