Across 10 comparable benchmarks, Claude Opus 4 has better reported results on 9 and worse on 0, with 1 tied.
Strong evidence10 of 10 shared results countedHow we compare
Claude Opus 4 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 | Claude Opus 4 | GPT-4.1 mini |
|---|---|---|
| Context window | 200K tokens | 1M tokens |
| Input / 1M | — | $0.400 |
| Output / 1M | — | $1.60 |
| Blended (4:1) | — | $0.424 |
| Status | Retired | Deprecated |
| Released | May 23, 2025 | April 14, 2025 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 8 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Claude Opus 4 ahead on 3 of 3 counted
Claude Opus 4 ahead on 1 of 2 counted
Claude Opus 4 ahead on 1 of 1 counted
Claude Opus 4 ahead on 1 of 1 counted
Claude Opus 4 ahead on 2 of 2 counted
No shared comparable results for Abstract reasoning, Computer & tool use, Research & search, Multimodal, Cybersecurity.
Published scores, with matching modes where available. Gaps show Claude Opus 4 relative to GPT-4.1 mini. Reading the results
| Benchmark | Claude Opus 4 | GPT-4.1 mini | Gap |
|---|---|---|---|
| Aider-PolyglotAgentic Development · Accuracy | 72.0Thinking · no tools · 32K | 32.4≠Normal · no tools | +39.6 pts#9 vs #32 of 47 |
| SWE-bench VerifiedRepository Engineering · Accuracy | 72.5Normal · no tools | 23.6Normal · no tools | +48.9 pts#52 vs #106 of 108 |
| Terminal Bench HardAgentic Development · Accuracy | 31.1Thinking · tools | 7.6≠Normal · tools | +23.5 pts#66 vs #122 of 157 |
| AIME 2024Mathematics · Accuracy | 76.0Normal · no tools | 49.6Normal · no tools | +26.4 pts#31 vs #43 of 54 |
| FrontierMathMathematics · Accuracy | 4.5Normal · no tools | 4.5Normal · no tools | =#30 vs #30 of 48 |
| GPQA DiamondScientific Reasoning · Accuracy | 70.1Normal · no tools | 65.0Normal · no tools | +5.1 pts#140 vs #157 of 200 |
| Fiction.liveBenchLong Reasoning · 16k-token score (%) | 61.1Normal · no tools | 44.4Normal · no tools | +16.7 pts#19 vs #25 of 28 |
| Creative WritingWriting | 1578Normal · no tools | 1145Normal · no tools | 1.38×#48 vs #93 of 121 |
| τ²-BenchService Workflows · Accuracy | 72.5Thinking · tools | 53.0≠Normal · tools | +19.5 pts#24 vs #31 of 40 |
| ECICapability Indices · ECI score (capability index, higher is better) | 143Reported best | 135Reported best | 1.06×#87 vs #112 of 168 |
Agentic Development · Accuracy
Repository Engineering · Accuracy
Agentic Development · Accuracy
Mathematics · Accuracy
Mathematics · Accuracy
Scientific Reasoning · Accuracy
Long Reasoning · 16k-token score (%)
Writing
Service Workflows · Accuracy
Capability Indices · ECI score (capability index, higher is better)
A dash means no result is available.
| Benchmark | Claude Opus 4 | GPT-4.1 mini |
|---|---|---|
| AIME2025 | 75.5 | — |
| FrontierMath - Tier 4 | 4.2 | — |
| FrontierMath v2 | — | 6.7 |
| HLE | 10.7 | — |
| IMO-ProofBench | 2.9 | — |
| IMO-ProofBench Advanced | 2.9 | — |
| MATH-500 | 98.2 | — |
| MMLU | — | 87.5 |
| MMLU-Pro | 87.3 | — |
| IC SWE-Lancer (Diamond) | — | 33.0 |
| LiveCodeBench | 56.6 | — |
| MMMU | 76.5 | — |
| MMMU-Pro | — | 58.7 |
| VPCT | 38.0 | — |
| τ²-Bench - Telecom | — | 48.9 |
| τ³-Banking | — | 5.4 |
| ARC-AGI-1 | 35.7 | — |
| ARC-AGI-2 | 8.6 | — |
| SimpleBench | 58.8 | — |
| GAIA | 64.8 | — |
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.
Claude Opus 4: Listed text rates; pricing tier not confirmed.
GPT-4.1 mini: Standard pricing. OpenAI official pricing (developers.openai.com/api/docs/pricing) verified 2026-11-13; standard tier; Deprecated; shutdown 2027-01-14 (replacement: gpt-6-luna)
| Price / 1M tokens | Claude Opus 4 | GPT-4.1 mini | Ratio |
|---|---|---|---|
| Input | — | $0.40 | — |
| Output | — | $1.60 | — |
| Cached input | — | $0.10 | — |
| Cache write | — | — | — |
| Blended | — | $0.424 | — |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
| Attribute | Claude Opus 4 | GPT-4.1 mini |
|---|---|---|
| Availability | Retired | Deprecated |
| Provider | Anthropic | OpenAI |
| Model type | Reasoning model | Chat model |
| First release | May 23, 2025 | April 14, 2025 |
| Context window | 200K tokens | 1M tokens |
| Max output | 32K 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 Claude Opus 4 or GPT-4.1 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.