Across 11 comparable benchmarks, Gemini-2.5-Pro-Preview-05-06 has better reported results on 11 and worse on 0.
Strong evidence11 of 11 shared results countedHow we compare
Gemini-2.5-Pro-Preview-05-06 is no longer available through its official API. API prices for this version are not shown.
Price basis: Listed rates vs standard rates. The price section below shows the applicable periods.
| Fact | Gemini-2.5-Pro-Preview-05-06 | GPT-4.1 |
|---|---|---|
| Context window | 1M tokens | 1M tokens |
| Input / 1M | — | $2.00 |
| Output / 1M | — | $8.00 |
| Blended (4:1) | — | $2.12 |
| Status | Retired | Deprecated |
| Released | May 6, 2025 | April 14, 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-2.5-Pro-Preview-05-06 ahead on 3 of 3 counted
Gemini-2.5-Pro-Preview-05-06 ahead on 4 of 4 counted
Gemini-2.5-Pro-Preview-05-06 ahead on 1 of 1 counted
Gemini-2.5-Pro-Preview-05-06 ahead on 1 of 1 counted
Gemini-2.5-Pro-Preview-05-06 ahead on 1 of 1 counted
No shared comparable results for Abstract reasoning, Computer & tool use, Research & search, Professional work & productivity, Cybersecurity.
Published scores, with matching modes where available. Gaps show Gemini-2.5-Pro-Preview-05-06 relative to GPT-4.1. Reading the results
| Benchmark | Gemini-2.5-Pro-Preview-05-06 | GPT-4.1 | Gap |
|---|---|---|---|
| Aider-PolyglotAgentic Development · Accuracy | 76.9Normal · no tools | 52.4Normal · no tools | +24.5 pts#6 vs #22 of 47 |
| LiveCodeBenchAlgorithmic Coding · Pass @K | 75.6Normal · no tools | 40.5Normal · no tools | 1.87×#44 vs #93 of 113 |
| SWE-bench VerifiedRepository Engineering · Accuracy | 63.2Normal · no tools | 54.6Normal · no tools | +8.6 pts#76 vs #85 of 108 |
| AIME2025Mathematics · Accuracy | 83.0Normal · no tools | 36.7Normal · no tools | +46.3 pts#50 vs #82 of 86 |
| FrontierMathMathematics · Accuracy | 10.3Normal · no tools | 5.5Normal · no tools | +4.8 pts#20 vs #28 of 48 |
| FrontierMath - Tier 4Mathematics · Accuracy | 2.1Normal · no tools | 0.0Normal · no tools | +2.1 pts#31 vs #44 of 50 |
| MATH-500Mathematics · Accuracy | 98.8Normal · no tools | 92.8Normal · no tools | +6.0 pts#7 vs #38 of 49 |
| GPQA DiamondScientific Reasoning · Accuracy | 83.0Normal · no tools | 66.3Normal · no tools | +16.7 pts#95 vs #152 of 200 |
| Fiction.liveBenchLong Reasoning · 16k-token score (%) | 66.7Normal · no tools | 63.9Normal · no tools | +2.8 pts#15 vs #17 of 28 |
| GeoBench ACWVisual Understanding · ACW country accuracy (%) | 86.0Normal · no tools | 72.0Normal · no tools | +14.0 pts#3 vs #20 of 32 |
| HLEKnowledge Exams · Accuracy | 17.8Normal · no tools | 5.4≠Reported best | +12.4 pts#111 vs #141 of 151 |
Agentic Development · Accuracy
Algorithmic Coding · Pass @K
Repository Engineering · Accuracy
Mathematics · Accuracy
Mathematics · Accuracy
Mathematics · Accuracy
Mathematics · Accuracy
Scientific Reasoning · Accuracy
Long Reasoning · 16k-token score (%)
Visual Understanding · ACW country accuracy (%)
Knowledge Exams · Accuracy
A dash means no result is available.
| Benchmark | Gemini-2.5-Pro-Preview-05-06 | GPT-4.1 |
|---|---|---|
| AIME 2024 | — | 48.1 |
| FrontierMath v2 | — | 6.0 |
| GSM8K | — | 95.9 |
| MMLU | — | 90.2 |
| MMLU-Pro | — | 80.5 |
| IC SWE-Lancer (Diamond) | — | 14.4 |
| SWE Manager Lancer (Diamond) | — | 35.1 |
| Terminal Bench Hard | — | 13.6 |
| WeirdML v2 | — | 39.0 |
| ECI | — | 137 |
| Creative Writing | — | 1420 |
| DROP | — | 89.2 |
| MMMU | 79.6 | — |
| MMMU-Pro | — | 61.2 |
| VPCT | 40.5 | — |
| τ²-Bench | — | 54.7 |
| τ²-Bench - Telecom | — | 34.0 |
| SimpleBench | — | 27.0 |
| GAIA | — | 49.7 |
| SimpleQA | 50.8 | — |
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-2.5-Pro-Preview-05-06: Listed text rates; pricing tier not confirmed.
| Price / 1M tokens | Gemini-2.5-Pro-Preview-05-06 | GPT-4.1 | Ratio |
|---|---|---|---|
| Input | — | $2.00 | — |
| Output | — | $8.00 | — |
| Cached input | — | $0.50 | — |
| Cache write | — | — | — |
| Blended | — | $2.12 | — |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
| Attribute | Gemini-2.5-Pro-Preview-05-06 | GPT-4.1 |
|---|---|---|
| Availability | Retired | Deprecated |
| Provider | Google Deep Mind | OpenAI |
| Model type | Reasoning model | Chat model |
| First release | May 6, 2025 | April 14, 2025 |
| Context window | 1M tokens | 1M tokens |
| Max output | 64K tokens | 32K tokens |
| Architecture | Undisclosed | Undisclosed |
| Documented capabilities | Reasoning, Multilingual | Multilingual |
| Input modalities | Text, Image | Text, Image |
| 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-2.5-Pro-Preview-05-06 or GPT-4.1? 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.