Across 14 comparable benchmarks, OpenAI o3-mini has better reported results on 9 and worse on 5.
Moderate evidence14 of 14 shared results countedHow we compare
Price basis: Standard rates vs listed rates. The price section below shows the applicable periods.
| Fact | GPT-4.1 | OpenAI o3-mini |
|---|---|---|
| Context window | 1M tokens | 200K tokens |
| Input / 1M | $2.00 | $1.10 |
| Output / 1M | $8.00 | $4.40 |
| Blended (4:1) | $2.12 | $1.36 |
| Status | Deprecated | Deprecated |
| Released | April 14, 2025 | January 31, 2025 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 10 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
GPT-4.1 ahead on 2 of 3 counted
GPT-4.1 ahead on 1 of 1 counted
No fixed-scale average — see the rows in Benchmark results
OpenAI o3-mini ahead on 5 of 5 counted
OpenAI o3-mini ahead on 1 of 1 counted
GPT-4.1 ahead on 1 of 1 counted
No shared comparable results for Computer & tool use, Research & search, Multimodal, Professional work & productivity, Cybersecurity.
Published scores, with matching modes where available. Gaps show GPT-4.1 relative to OpenAI o3-mini. Reading the results
| Benchmark | GPT-4.1 | OpenAI o3-mini | Gap |
|---|---|---|---|
| Aider-PolyglotAgentic Development · Accuracy | 52.4Normal · no tools | 60.4≠Thinking High · no tools | −8.0 pts#22 vs #15 of 47 |
| SWE-bench VerifiedRepository Engineering · Accuracy | 54.6Normal · no tools | 40.8≠Thinking · no tools | +13.8 pts#85 vs #99 of 108 |
| Terminal Bench HardAgentic Development · Accuracy | 13.6Normal · tools | 6.8≠Thinking · tools | +6.8 pts#110 vs #123 of 157 |
| SimpleBenchCommonsense · Score (AVG@5) | 27.0Normal · no tools | 22.8≠Thinking High · no tools | 1.18×#91 vs #96 of 106 |
| AIME 2024Mathematics · Accuracy | 48.1Normal · no tools | 60.0≠Thinking · no tools | −11.9 pts#44 vs #37 of 54 |
| AIME2025Mathematics · Accuracy | 36.7Normal · no tools | 86.5≠Thinking · no tools | −49.8 pts#82 vs #44 of 86 |
| FrontierMath - Tier 4Mathematics · Accuracy | 0.0Normal · no tools | 4.2≠Thinking High · no tools | −4.2 pts#44 vs #21 of 50 |
| FrontierMath v2Mathematics · Accuracy (verification_code) | 6.0Reported best | 18.6≠Thinking High · tools | −12.6 pts#85 vs #81 of 85 |
| MATH-500Mathematics · Accuracy | 92.8Normal · no tools | 98.5≠Thinking High · no tools | −5.7 pts#38 vs #10 of 49 |
| GPQA DiamondScientific Reasoning · Accuracy | 66.3Normal · no tools | 70.6≠Thinking · no tools | −4.3 pts#152 vs #137 of 200 |
| Fiction.liveBenchLong Reasoning · 16k-token score (%) | 63.9Normal · no tools | 50.0≠Thinking Medium · no tools | +13.9 pts#17 vs #22 of 28 |
| HLEKnowledge Exams · Accuracy | 5.4Reported best | 13.4≠Thinking · no tools | −8.0 pts#141 vs #119 of 151 |
| MMLUKnowledge Exams · Accuracy | 90.2Normal · no tools | 84.9≠Thinking · no tools | +5.3 pts#6 vs #37 of 114 |
| ECICapability Indices · ECI score (capability index, higher is better) | 137Reported best | 140Reported best | 0.97×#108 vs #95 of 168 |
Agentic Development · Accuracy
Repository Engineering · Accuracy
Agentic Development · Accuracy
Commonsense · Score (AVG@5)
Mathematics · Accuracy
Mathematics · Accuracy
Mathematics · Accuracy
Mathematics · Accuracy (verification_code)
Mathematics · Accuracy
Scientific Reasoning · Accuracy
Long Reasoning · 16k-token score (%)
A dash means no result is available.
| Benchmark | GPT-4.1 | OpenAI o3-mini |
|---|---|---|
| CritPt | — | 0.3 |
| FrontierMath | 5.5 | — |
| FrontierMath Tier 4 v2 | — | 0.0 |
| GSM8K | 95.9 | — |
| MMLU-Pro | 80.5 | — |
| SciCode | — | 42.8 |
| CodeForces | — | 2073 |
| IC SWE-Lancer (Diamond) | 14.4 | — |
| LiveCodeBench | 40.5 | — |
| SWE Manager Lancer (Diamond) | 35.1 | — |
| WeirdML v2 | 39.0 | — |
| Creative Writing | 1420 | — |
| DROP | 89.2 | — |
| GDP.pdf | — | 2.0 |
| GeoBench ACW | 72.0 | — |
| MMMU-Pro | 61.2 | — |
| τ²-Bench | 54.7 | — |
| τ²-Bench - Telecom | 34.0 | — |
| τ³-Banking | — | 5.2 |
| ARC-AGI-1 | — | 34.5 |
| ARC-AGI-2 | — | 3.0 |
| 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 costs55%morethan OpenAI o3-mini per million tokens.Using standard rates vs listed rates at this token mix.
OpenAI o3-mini: Listed text rates; pricing tier not confirmed.
| Price / 1M tokens | GPT-4.1 | OpenAI o3-mini | Ratio |
|---|---|---|---|
| Input | $2.00 | $1.10 | 1.82× |
| Output | $8.00 | $4.40 | 1.82× |
| Cached input | $0.50 | $0.55 | 0.91× |
| Cache write | — | — | — |
| Blended | $2.12 | $1.36 | 1.55× |
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.
| Attribute | GPT-4.1 | OpenAI o3-mini |
|---|---|---|
| Availability | Deprecated | Deprecated |
| Provider | OpenAI | OpenAI |
| Model type | Chat model | Reasoning model |
| First release | April 14, 2025 | January 31, 2025 |
| Context window | 1M tokens | 200K tokens |
| Max output | 32K tokens | 100K 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 OpenAI o3-mini? 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.