o1 vs o3-deep-research vs Claude Opus 4
No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.
Price in rating: Excluded · Include price
OpenAI
o1
64/100- ECI141.2
- Price$15.00 / $60.00
- Context200K
OpenAI
o3-deep-research
52/100- ECI—
- Price$9.00 / $36.00
- Context200K
Anthropic
Claude Opus 4
58/100- ECI142.9
- Price$15.00 / $75.00
- Context200K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (o1 64/100, Claude Opus 4 58/100, o3-deep-research 52/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceo3-deep-researcho3-deep-research $15.75 · o1 $26.25 · Claude Opus 4 $30.00 per 1M tokens (3:1 blend)
- Longest contextAbout the sameo1 200,000 · o3-deep-research 200,000 · Claude Opus 4 200,000 tokens
- Widest inputso1 and Claude Opus 4o1: Text, Images, PDFs · o3-deep-research: Text, Images · Claude Opus 4: Text, Images, PDFs
- Self-hostingNo confirmed open weightsAll three are available only through APIs
| Measure | Weight | o1 | o3-deep-research | Claude Opus 4 |
|---|---|---|---|---|
| Inputs & features | 60% | 80 | 60 | 70 |
| Context window | 40% | 39 | 39 | 39 |
| Specs only | 100% | 64/100 | 52/100 | 58/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 141.2 | — | 142.9 (best) |
| ECI rank | #109 of 158 | — | #101 of 158 (best) |
| GPQA DiamondGraduate-level science questions | 76.8% (best) | — | 76.3% |
| FrontierMath Tiers 1–3Research-level mathematics | 14.7% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 73.3% (best) | — | 64.4% |
| SWE-bench VerifiedFixing real GitHub issues | — | — | 70.7% |
| SimpleQA VerifiedShort factual questions | 41.1% | — | — |
| Price per million tokens | |||
| Input | $15.00 | $9.00 (best) | $15.00 |
| Output | $60.00 | $36.00 (best) | $75.00 |
| Cached input | $7.50 | — | — |
| Blended (3:1) | $26.25 | $15.75 (best) | $30.00 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official OpenAI API | Median of 1 providers | Median of 7 providers |
| Limits | |||
| Context window | 200,000 tokens | 200,000 tokens | 200,000 tokens |
| Max output | 100,000 tokens (best) | 100,000 tokens (best) | 32,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | Yes | No | Yes |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yeslow · medium · high | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | Proprietary | Proprietary |
| API model ID | o1 | — | — |
| API providers | 9 (best) | 1 | 8 |
| Released | Dec 5, 2024 | Jun 26, 2025 | May 22, 2025 |
| Knowledge cutoff | Sep 2023 | May 2024 | Mar 31, 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
o1$270.00
o3-deep-research$162.00
Claude Opus 4$300.00
Which should you choose?
Which is better: o1, o3-deep-research or Claude Opus 4?
There is not enough shared capability evidence to name an overall winner. The scores (o1 64/100, Claude Opus 4 58/100, o3-deep-research 52/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, o1, o3-deep-research or Claude Opus 4?
o3-deep-research is cheaper at $9.00 input / $36.00 output per million tokens (median across 1 API provider). o1 costs $15.00 input / $60.00 output per million tokens (official OpenAI API price); Claude Opus 4 costs $15.00 input / $75.00 output per million tokens (median across 7 API providers). At a typical mix of three input tokens to one output token, that is $15.75 per million tokens for o3-deep-research versus $26.25 for o1 (1.7× as much) and $30.00 for Claude Opus 4 (1.9× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. o1 has an ECI of 141.2, o3-deep-research has not been scored yet and Claude Opus 4 has an ECI of 142.9.
Which is better for coding?
There are no published SWE-bench Verified results for o1 and o3-deep-research yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
o1, o3-deep-research and Claude Opus 4 share the same 200,000-token context window. Maximum output per response: o1 up to 100,000, o3-deep-research up to 100,000, Claude Opus 4 up to 32,000 tokens.
Which can read images, PDFs, audio or video?
o1 accepts text, images and PDFs; o3-deep-research accepts text and images; Claude Opus 4 accepts text, images and PDFs. o1 handles the widest range of inputs.
Are any of these open source?
No. o1, o3-deep-research and Claude Opus 4 are proprietary and only available through APIs and apps.
Which is newer?
o3-deep-research is the newest, released Jun 26, 2025. Claude Opus 4 came out May 22, 2025; o1 came out Dec 5, 2024. Knowledge cutoff: o1 Sep 2023, o3-deep-research May 2024, Claude Opus 4 Mar 31, 2025.
How do you decide the winner?
This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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 Nov 18, 2026.