Comparison
Claude Opus 5.5 vs GPT-6.1 Terra
Verdict
Claude Opus 5.5 scores higher — 59 vs 51, both at their highest reasoning tier (max). Claude Opus 5.5 costs 10.5× as much per task ($10.04 vs $0.96). Per index point: $0.1702 for Claude Opus 5.5 vs $0.0188 for GPT-6.1 Terra.
Claude Opus 5.5 ranks #68 of 73 on cost per task among closed-source models above $1 per million tokens (blended 3:1) that AA prices; the class holds 237 models. GPT-6.1 Terra ranks #13 of 73 on cost per task in that same class of 237.
Our pick: GPT-6.1 Terra. The price sentences above use it as the baseline; scope: API access.
- Claude Opus 5.5 — Take Claude Opus 5.5 when the score itself is what you are buying: 59 vs 51 index points, $10.04 vs $0.96 per task ($1.14 per extra point), 25.0 vs 14.0 minutes.
- GPT-6.1 Terra — Take GPT-6.1 Terra when the bill or the clock binds: 51 vs 59 index points, $0.96 vs $10.04 per task, 14.0 vs 25.0 minutes — it gives up 8 points and saves $9.08 per task and is 11.0 minutes faster.
Side by side
| Attribute | Claude Opus 5.5 | GPT-6.1 Terra |
|---|---|---|
| Intelligence Index | 59 | 51 |
| Cost per task (USD) | $10.04 | $0.96 |
| Minutes per task | 25.0 min | 14.0 min |
| Input modalities | text, image | text, image |
| Cost per index point | $0.1702 | $0.0188 |
| Input $/M tokens | $4.00 | $1.00 |
| Output $/M tokens | $20.00 | $5.00 |
| Cache discount | 95% | 95% |
| Context window | 1M | 1M |
| Input tokens (Intelligence Index) | 15.60B | 5.57B |
| Output tokens (Intelligence Index) | 218M | 99M |
| Output/input ratio | 1.4% | 1.785% |
| Reasoning tier | max | max |
Where each wins
Claude Opus 5.5
- Intelligence Index: 59 vs 51
- Level on Input modalities (text, image)
- Level on Cache discount (95%)
- Level on Context window (1M)
GPT-6.1 Terra
- Cost per task (USD): $0.96 vs $10.04
- Minutes per task: 14.0 min vs 25.0 min
- Cost per index point: $0.0188 vs $0.1702
- Input $/M tokens: $1.00 vs $4.00
- Output $/M tokens: $5.00 vs $20.00
Sources and conflicts
- OpenRouter lists
anthropic/claude-opus-5.5(exact match). Input price: AA $4 per million tokens vs OpenRouter $4. This page uses AA's figure throughout and does not average the two. - OpenRouter lists
openai/gpt-6.1-terra(exact match). Input price: AA $1 per million tokens vs OpenRouter $1. This page uses AA's figure throughout and does not average the two. - Prices and input modalities come from Artificial Analysis only; the second source is used to cross-check, never to union or average.
- A differing modality string is not a conflict: AA records what the model accepts, a provider records what its own route declares. Different objects, both reported here.
Data
Data as of 2026-11-12 · Artificial Analysis Intelligence Index v5.0.1, highest reasoning effort per model. Prices from the same pages.
Every cell is tied to a verbatim excerpt of that model's own Artificial Analysis page.
N/A (AA: Unknown) = AA publishes no value in that cell. It is not 0, and it is not 'unreleased'.
'not applicable (AA prints `-`)' = AA lists no per-token price for this model, so the cell does not exist. It is not the same as N/A and not the same as a withheld figure.
'not computable (…)' = the cell is derived from two others and one of them has no figure. The bracket names which one — it is not a value, and it is not the same as N/A.
'not printed on its AA page' = the page lists prices but withholds that figure; it is not treated as equal to anything.
'unverified' = we have not read that cell on that page. It is not a value and not a tie.
Token rows are AA's Verbosity block: input and output totals for the whole Intelligence Index run. 'Output/input ratio' is AA's own label and means output / input — it is not output's share of the total.
AA publishes no measured cache-hit rate for either model (it prints a fixed 7:2:1 cache-hit/input/output blend instead), so no cell records one.