o1 vs Claude Opus 4 vs Claude Sonnet 3.5 v2
Too close to call on our weighted score (o1 49, Claude Opus 4 48, Claude Sonnet 3.5 v2 44). The right pick depends on what you value most.
OpenAIo1
49/100- ECI141.9
- Price$15.00 / $60.00
- Context200K
AnthropicClaude Opus 4
48/100- ECI142.7
- Price$15.00 / $75.00
- Context200K
- Anthropic
Claude Sonnet 3.5 v2
44/100- ECI133.5
- Price$3.00 / $15.00
- Context200K
Too close to call
It is close. Our weighted score puts them within 1 points (o1 49/100, Claude Opus 4 48/100, Claude Sonnet 3.5 v2 44/100), so choose by what matters most for your work: Claude Opus 4 for raw capability and Claude Sonnet 3.5 v2 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityClaude Opus 4Capabilities Index (ECI): Claude Opus 4 142.7 · o1 141.9 · Claude Sonnet 3.5 v2 133.5
- Lowest priceClaude Sonnet 3.5 v2Claude Sonnet 3.5 v2 $6.00 · o1 $26.25 · Claude Opus 4 $30.00 per 1M tokens (3:1 blend)
- Longest contextAbout the sameo1 200,000 · Claude Opus 4 200,000 · Claude Sonnet 3.5 v2 200,000 tokens
- Widest inputsSame inputso1: Text, Images, PDFs · Claude Opus 4: Text, Images, PDFs · Claude Sonnet 3.5 v2: Text, Images, PDFs
- Self-hostingNo open weightsAll three are available only through APIs
| Measure | Weight | o1 | Claude Opus 4 | Claude Sonnet 3.5 v2 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 68 | 69 | 57 |
| Price | 25% | 0 | 0 | 13 |
| Inputs & features | 15% | 80 | 70 | 60 |
| Context window | 10% | 32 | 32 | 32 |
| Overall | 100% | 49/100 | 48/100 | 44/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | o1OpenAI | Claude Opus 4Anthropic | Claude Sonnet 3.5 v2Anthropic |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 141.9 | 142.7 (best) | 133.5 |
| ECI rank | #92 of 148 | #87 of 148 (best) | #119 of 148 |
| GPQA DiamondGraduate-level science questions | 76.8% (best) | 76.3% | 55.3% |
| FrontierMath Tiers 1–3Research-level mathematics | 14.7% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 73.3% (best) | 64.4% | 8.5% |
| SWE-bench VerifiedFixing real GitHub issues | — | 70.7% | — |
| SimpleQA VerifiedShort factual questions | 41.1% | — | — |
| Price per million tokens | |||
| Input | $15.00 | $15.00 | $3.00 (best) |
| Output | $60.00 | $75.00 | $15.00 (best) |
| Cached input | $7.50 | — | — |
| Blended (3:1) | $26.25 | $30.00 | $6.00 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official OpenAI API | Median of 5 providers | Median of 1 providers |
| Limits | |||
| Context window | 200,000 tokens | 200,000 tokens | 200,000 tokens |
| Max output | 100,000 tokens (best) | 32,000 tokens | 8,192 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 | Yeslow · medium · high | Yes | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | Proprietary | Proprietary |
| API model ID | o1 | — | — |
| API providers | 9 (best) | 5 | 1 |
| Released | Dec 5, 2024 | May 22, 2025 | Oct 22, 2024 |
| Knowledge cutoff | Sep 2023 | Mar 31, 2025 | Apr 30, 2024 |
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
- Claude Opus 4$300.00
- Claude Sonnet 3.5 v2$60.00
Which should you choose?
Which is better: o1, Claude Opus 4 or Claude Sonnet 3.5 v2?
It is close. Our weighted score puts them within 1 points (o1 49/100, Claude Opus 4 48/100, Claude Sonnet 3.5 v2 44/100), so choose by what matters most for your work: Claude Opus 4 for raw capability and Claude Sonnet 3.5 v2 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, o1, Claude Opus 4 or Claude Sonnet 3.5 v2?
Claude Sonnet 3.5 v2 is cheaper at $3.00 input / $15.00 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 5 API providers). At a typical mix of three input tokens to one output token, that is $6.00 per million tokens for Claude Sonnet 3.5 v2 versus $26.25 for o1 (4.4× as much) and $30.00 for Claude Opus 4 (5× as much).
Which scores higher on benchmarks?
Claude Opus 4 scores higher on the Capabilities Index (ECI): Claude Opus 4 142.7 (#87 of 148), o1 141.9 (#92 of 148) and Claude Sonnet 3.5 v2 133.5 (#119 of 148). The confidence ranges of the top two overlap (140.2–144.2 vs 139.7–143.1), so treat the gap as small. On individual benchmarks: GPQA Diamond — o1 76.8%, Claude Opus 4 76.3%, Claude Sonnet 3.5 v2 55.3%; OTIS Mock AIME 2024–2025 — o1 73.3%, Claude Opus 4 64.4%, Claude Sonnet 3.5 v2 8.5%.
Which is better for coding?
There are no published SWE-bench Verified results for o1 and Claude Sonnet 3.5 v2 yet, so there is no like-for-like coding score. On overall capability, Claude Opus 4 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
o1, Claude Opus 4 and Claude Sonnet 3.5 v2 share the same 200,000-token context window. Maximum output per response: o1 up to 100,000, Claude Opus 4 up to 32,000, Claude Sonnet 3.5 v2 up to 8,192 tokens.
Which can read images, PDFs, audio or video?
o1 accepts text, images and PDFs; Claude Opus 4 accepts text, images and PDFs; Claude Sonnet 3.5 v2 accepts text, images and PDFs. They handle the same number of input types.
Are any of these open source?
No. o1, Claude Opus 4 and Claude Sonnet 3.5 v2 are proprietary and only available through APIs and apps.
Which is newer?
Claude Opus 4 is the newest, released May 22, 2025. o1 came out Dec 5, 2024; Claude Sonnet 3.5 v2 came out Oct 22, 2024. Knowledge cutoff: o1 Sep 2023, Claude Opus 4 Mar 31, 2025, Claude Sonnet 3.5 v2 Apr 30, 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.
