In short
How they differ.
Worked out from the figures below. Prices and specs are the makers' own, read Oct 20, 2026.
- Claude Haiku 5.5 is cheaper per output token: $0.50 against $10 per million tokens, so GPT-6.1 Sol costs 20 times as much.
- GPT-6.1 Sol reads more at once: a context window of 1M tokens against 1M.
- On the 7 independent boards that rank both, GPT-6.1 Sol places higher on 6 and Claude Haiku 5.5 on 1.
Side by side
The specs.
| Claude Haiku 5.5 | GPT-6.1 Sol | |
|---|---|---|
| Made by | Anthropic · US | OpenAI · US |
| Released | Oct 7, 2026 | Sep 29, 2026 |
| Price per 1M tokens | $0.10 in / $0.50 out | $2 in / $10 out |
| Context window | 1M | 1M |
| Takes in | text, image | text, image |
| Download and run it yourself | No | No |
| Size | Not published | Not published |
| Maker says | “For high-volume, latency-sensitive tasks such as classification, extraction, and routing” | “Near-Astra performance for complex work at a lower cost.” |
| Sources | Prices, Oct 20, 2026 · Description | Prices, Oct 20, 2026 · Description |
Independent tests
Where they place.
Position on each board we follow (1 is best). Epoch AI's and Vectara's scores are shown; the other boards are linked for their own figures.
| Board | Claude Haiku 5.5 | GPT-6.1 Sol |
|---|---|---|
| Epoch Capabilities IndexEpoch AI, Oct 20, 2026 | #14158.98 | #3166.32 |
| LMArena coding chatsLMArena, Oct 15, 2026 | Not listed | #10 |
| LMArena WebDevLMArena, Oct 19, 2026 | Not listed | #4 |
| LMArena visionLMArena, Oct 19, 2026 | Not listed | #9 |
| LMArena Agent ArenaLMArena, Oct 19, 2026 | Not listed | #4 |
| SWE-Bench ProScale AI, Sep 22, 2026 | #16 | #7 |
| MultiChallengeScale AI, Feb 3, 2026 | #6 | #1 |
| Vals IndexVals AI, Oct 19, 2026 | #10 | #7 |
| Terminal-Bench 4.0Vals AI, Oct 19, 2026 | #15 | #7 |
| Vibe Code BenchVals AI, Oct 18, 2026 | #3 | #8 |
| ProofBenchVals AI, Oct 12, 2026 | #11 | #5 |
More comparisons