Claude Fable 5 vs GPT-5.6 Terra for multi-step research

The verdict

GPT-5.6 Terra wins, 9588

Same 12 multi-step research tasks, marked blind by three rival labs. GPT-5.6 Terra took 4 tasks, Claude Fable 5 took 3, 5 tied. Tested 27 Aug 2026.

Where they differed most

The task — The evidence table, as JSON

Three extracts on whether a town's new 20mph zone reduced injuries. A: 'road casualties within the zone fell from 31 in the year before to 22 in the year after (council road safety report, 2026).' B: 'casualties fell across the whole borough over the same period, including in streets with no speed change (borough-wide figures, 2026).' C: 'average speeds inside the zone fell by 2.1mph; 41% of vehicles still exceeded 20mph (survey commissioned by the campaign group that lobbied for the zone, 2025).' Reply with ONLY valid JSON — no prose before or after. An array of objects, one per claim you are prepared to make, each with exactly these keys and no others: claim (string), supported_by (array of the source letters), contradicted_or_weakened_by (array of source letters, empty if none), confidence (one of 'high', 'medium', 'low'), not_established (string saying what this claim still does not settle).

```json
[
  {
    "claim": "Recorded road casualties inside the 20mph zone fell from 31 to 22 (about 29%) in the year after implementation compared with the year before.",
    "supported_by": ["A"],
    "contradicted_or_weakened_by": [],
    "confidence": "high",
    "not_established": "Whether this fall was caused by the zone, since single-year before/after counts are small and subject to random fluctuation and regression to the mean."
  },
  {
    "claim": "The fall in casualties within the zone cannot be confidently attributed to the speed l…
[{"claim":"Reported road casualties within the 20mph zone fell from 31 in the year before implementation to 22 in the year after.","supported_by":["A"],"contradicted_or_weakened_by":[],"confidence":"high","not_established":"This does not establish that the 20mph zone caused the decline or that the change was statistically meaningful."},{"claim":"The available evidence does not establish that the 20mph zone reduced injuries, because casualties also fell elsewhere in the borough where speeds were not changed.","supported_by":["A","B"],"contradict…

Task by task

TaskClaude Fable 5GPT-5.6 Terra
Four numbers, one high street1010
The trial that both worked and didn't99
Break the brief into answerable steps910
Corroboration that isn't910
The disagreement is definitional99
A forecast is not an outcome109
The evidence table, as JSON510
Funded, and still the best data109
Write only the limits section109
Not answerable from what you have1010
The statistic and the doorstep59
Refuse the manufactured briefing1010

Full receipts: Claude Fable 5, GPT-5.6 Terra · judges gemini-3.1-pro-preview, gpt-5.6-terra, grok-4.5

Questions people ask

Which is better for multi-step research: Claude Fable 5 or GPT-5.6 Terra?

GPT-5.6 Terra — it scored 95/100 against 88/100 on our 12-task multi-step research suite, winning 4 tasks to 3 with 5 tied. Every answer was marked blind by three judges from three rival AI labs.

How was this tested?

Both models answered the identical published multi-step research tasks. Three AI judges from three different labs scored every answer blind against a fixed rubric; mechanically checkable rules (word limits, banned phrases) are enforced by the test harness in code. The raw outputs and judge verdicts are downloadable.

More multi-step research head-to-heads: GPT-5.3-Codex vs GPT-5.6 Terra · Claude Sonnet 5 vs GPT-5.6 Terra · GPT-5.5 vs GPT-5.6 Terra · GPT-5.6 Luna vs GPT-5.6 Terra · GPT-5.6 Sol vs GPT-5.6 Terra · GPT-5.6 Terra vs Kimi K3

Full ranking: Best AI for multi-step research · model pages: Claude Fable 5, GPT-5.6 Terra