Across 5 comparable benchmarks, Gemini 2.5 Deep Think has better reported results on 5 and worse on 0.
Moderate evidence5 of 5 shared results countedHow we compare
Price basis: Standard rates. The price section below shows the applicable periods.
| Fact | GPT-4.1 | Gemini 2.5 Deep Think |
|---|---|---|
| Context window | 1M tokens | 1M tokens |
| Input / 1M | $2.00 | $0.400 |
| Output / 1M | $8.00 | $1.60 |
| Blended (4:1) | $2.12 | $0.640 |
| Status | Deprecated | Available |
| Released | April 14, 2025 | August 1, 2025 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 3 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Gemini 2.5 Deep Think ahead on 1 of 1 counted
No fixed-scale average — see the rows in Benchmark results
Gemini 2.5 Deep Think ahead on 3 of 3 counted
No shared comparable results for Abstract reasoning, Science & health, Computer & tool use, Research & search, Long context, Multimodal, Professional work & productivity, Cybersecurity.
Published scores, with matching modes where available. Gaps show GPT-4.1 relative to Gemini 2.5 Deep Think. Reading the results
| Benchmark | GPT-4.1 | Gemini 2.5 Deep Think | Gap |
|---|---|---|---|
| LiveCodeBenchAlgorithmic Coding · Pass @K | 40.5Normal · no tools | 87.6≠Deep Thinking · no tools | 0.46×#93 vs #16 of 113 |
| AIME2025Mathematics · Accuracy | 36.7Normal · no tools | 99.2≠Deep Thinking · no tools | −62.5 pts#82 vs #11 of 86 |
| FrontierMathMathematics · Accuracy | 5.5Normal · no tools | 29.0≠Deep Thinking · no tools | −23.5 pts#28 vs #11 of 48 |
| FrontierMath - Tier 4Mathematics · Accuracy | 0.0Normal · no tools | 10.4Normal · no tools | −10.4 pts#44 vs #15 of 50 |
| HLEKnowledge Exams · Accuracy | 5.4Reported best | 34.8≠Deep Thinking · no tools | −29.4 pts#141 vs #83 of 151 |
Algorithmic Coding · Pass @K
Mathematics · Accuracy
Mathematics · Accuracy
Mathematics · Accuracy
Knowledge Exams · Accuracy
A dash means no result is available.
| Benchmark | GPT-4.1 | Gemini 2.5 Deep Think |
|---|---|---|
| AIME 2024 | 48.1 | — |
| FrontierMath v2 | 6.0 | — |
| GPQA Diamond | 66.3 | — |
| GSM8K | 95.9 | — |
| IMO-ProofBench | — | 37.6 |
| MATH-500 | 92.8 | — |
| MMLU | 90.2 | — |
| MMLU-Pro | 80.5 | — |
| Aider-Polyglot | 52.4 | — |
| IC SWE-Lancer (Diamond) | 14.4 | — |
| SWE Manager Lancer (Diamond) | 35.1 | — |
| SWE-bench Verified | 54.6 | — |
| Terminal Bench Hard | 13.6 | — |
| WeirdML v2 | 39.0 | — |
| ECI | 137 | — |
| Creative Writing | 1420 | — |
| DROP | 89.2 | — |
| Fiction.liveBench | 63.9 | — |
| GeoBench ACW | 72.0 | — |
| MMMU-Pro | 61.2 | — |
| τ²-Bench | 54.7 | — |
| τ²-Bench - Telecom | 34.0 | — |
| SimpleBench | 27.0 | — |
| GAIA | 49.7 | — |
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%
GPT-4.1 costs231%morethan Gemini 2.5 Deep Think per million tokens — 3.3× the price.Using standard rates at this token mix.
| Price / 1M tokens | GPT-4.1 | Gemini 2.5 Deep Think | Ratio |
|---|---|---|---|
| Input | $2.00 | $0.40 | 5.00× |
| Output | $8.00 | $1.60 | 5.00× |
| Cached input | $0.50 | — | — |
| Cache write | — | — | — |
| Blended | $2.12 | $0.64 | 3.31× |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
| Attribute | GPT-4.1 | Gemini 2.5 Deep Think |
|---|---|---|
| Availability | Deprecated | Available |
| Provider | OpenAI | Google Deep Mind |
| Model type | Chat model | Chat model |
| First release | April 14, 2025 | August 1, 2025 |
| Context window | 1M tokens | 1M tokens |
| Max output | 32K tokens | 16K tokens |
| Architecture | Undisclosed | Undisclosed |
| Documented capabilities | Multilingual | Reasoning, Multilingual |
| Input modalities | Text, Image | Text |
| 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 GPT-4.1 or Gemini 2.5 Deep Think? 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.