GPT-4.1 vs o3 vs Claude Sonnet 3.7
o3 comes out ahead, 58 to 53 and 50 on our weighted score.
OpenAIGPT-4.1
53/100- ECI136.8
- Price$2.00 / $8.00
- Context1.05M
- Our pickOpenAI
o3
58/100- ECI146.9
- Price$2.00 / $8.00
- Context200K
AnthropicClaude Sonnet 3.7
50/100- ECI141.2
- Price$3.00 / $15.00
- Context200K
o3 is our pick
o3 is the better all-round choice, scoring 58/100 against GPT-4.1 (53) and Claude Sonnet 3.7 (50). It leads on capability and inputs & features. GPT-4.1 wins on context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- Capabilityo3Capabilities Index (ECI): o3 146.9 · Claude Sonnet 3.7 141.2 · GPT-4.1 136.8
- Lowest priceGPT-4.1 and o3GPT-4.1 $3.50 · o3 $3.50 · Claude Sonnet 3.7 $6.00 per 1M tokens (3:1 blend)
- Longest contextGPT-4.1GPT-4.1 1,047,576 · o3 200,000 · Claude Sonnet 3.7 200,000 tokens
- Widest inputsSame inputsGPT-4.1: Text, Images, PDFs · o3: Text, Images, PDFs · Claude Sonnet 3.7: Text, Images, PDFs
- Self-hostingNo open weightsAll three are available only through APIs
| Measure | Weight | GPT-4.1 | o3 | Claude Sonnet 3.7 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 61 | 74 | 67 |
| Price | 25% | 24 | 24 | 13 |
| Inputs & features | 15% | 70 | 80 | 70 |
| Context window | 10% | 61 | 32 | 32 |
| Overall | 100% | 53/100 | 58/100 | 50/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | GPT-4.1OpenAI | o3OpenAI | Claude Sonnet 3.7Anthropic |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 136.8 | 146.9 (best) | 141.2 |
| ECI rank | #111 of 148 | #63 of 148 (best) | #96 of 148 |
| GPQA DiamondGraduate-level science questions | 66.9% | 81.8% (best) | 79.7% |
| FrontierMath Tiers 1–3Research-level mathematics | 6.0% | 33.3% (best) | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 38.3% | 84.4% (best) | 57.8% |
| SWE-bench VerifiedFixing real GitHub issues | 48.5% | 62.3% (best) | 61.0% |
| SimpleQA VerifiedShort factual questions | 31.1% | 49.4% (best) | — |
| Price per million tokens | |||
| Input | $2.00 (best) | $2.00 (best) | $3.00 |
| Output | $8.00 (best) | $8.00 (best) | $15.00 |
| Cached input | $0.50 | $0.50 | — |
| Blended (3:1) | $3.50 (best) | $3.50 (best) | $6.00 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official OpenAI API | Official OpenAI API | Median of 3 providers |
| Limits | |||
| Context window | 1,047,576 tokens (best) | 200,000 tokens | 200,000 tokens |
| Max output | 32,768 tokens | 100,000 tokens (best) | 64,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | Yes | Yes | Yes |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yeslow · medium · high | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | No |
| Availability | |||
| Weights | Proprietary | Proprietary | Proprietary |
| API model ID | gpt-4.1 | o3 | — |
| API providers | 25 (best) | 18 | 3 |
| Released | Apr 14, 2025 | Apr 16, 2025 | Feb 19, 2025 |
| Knowledge cutoff | Apr 2024 | May 2024 | Oct 31, 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- GPT-4.1$36.00
- o3$36.00
- Claude Sonnet 3.7$60.00
Which should you choose?
Which is better: GPT-4.1, o3 or Claude Sonnet 3.7?
o3 is the better all-round choice, scoring 58/100 against GPT-4.1 (53) and Claude Sonnet 3.7 (50). It leads on capability and inputs & features. GPT-4.1 wins on context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, GPT-4.1, o3 or Claude Sonnet 3.7?
GPT-4.1 is cheaper at $2.00 input / $8.00 output per million tokens (official OpenAI API price). o3 costs $2.00 input / $8.00 output per million tokens (official OpenAI API price); Claude Sonnet 3.7 costs $3.00 input / $15.00 output per million tokens (median across 3 API providers). At a typical mix of three input tokens to one output token, that is $3.50 per million tokens for GPT-4.1 versus $3.50 for o3 (1× as much) and $6.00 for Claude Sonnet 3.7 (1.7× as much).
Which scores higher on benchmarks?
o3 scores higher on the Capabilities Index (ECI): o3 146.9 (#63 of 148), Claude Sonnet 3.7 141.2 (#96 of 148) and GPT-4.1 136.8 (#111 of 148). Their confidence ranges do not overlap (144.9–148.6 vs 138.7–142.9), so the gap is a real one. On individual benchmarks: GPQA Diamond — o3 81.8%, Claude Sonnet 3.7 79.7%, GPT-4.1 66.9%; OTIS Mock AIME 2024–2025 — o3 84.4%, Claude Sonnet 3.7 57.8%, GPT-4.1 38.3%; SWE-bench Verified — o3 62.3%, Claude Sonnet 3.7 61.0%, GPT-4.1 48.5%.
Which is better for coding?
o3 resolves more real GitHub issues on SWE-bench Verified: o3 62.3%, Claude Sonnet 3.7 61.0% and GPT-4.1 48.5%. All three support tool calling for agent workflows.
Which has the bigger context window?
GPT-4.1 has the largest context window at 1,047,576 tokens, against 200,000 for o3 and 200,000 for Claude Sonnet 3.7. Maximum output per response: GPT-4.1 up to 32,768, o3 up to 100,000, Claude Sonnet 3.7 up to 64,000 tokens.
Which can read images, PDFs, audio or video?
GPT-4.1 accepts text, images and PDFs; o3 accepts text, images and PDFs; Claude Sonnet 3.7 accepts text, images and PDFs. They handle the same number of input types.
Are any of these open source?
No. GPT-4.1, o3 and Claude Sonnet 3.7 are proprietary and only available through APIs and apps.
Which is newer?
o3 is the newest, released Apr 16, 2025. GPT-4.1 came out Apr 14, 2025; Claude Sonnet 3.7 came out Feb 19, 2025. Knowledge cutoff: GPT-4.1 Apr 2024, o3 May 2024, Claude Sonnet 3.7 Oct 31, 2024.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.
