Claude Opus 4.6 vs GPT-5.5 for multi-step research

The verdict

GPT-5.5 wins, 9185

Same 12 multi-step research tasks, marked blind by three rival labs. GPT-5.5 took 4 tasks, Claude Opus 4.6 took 2, 6 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": "The number of road casualties recorded inside the 20mph zone fell from 31 to 22 in the year following its introduction.",
    "supported_by": ["A"],
    "contradicted_or_weakened_by": [],
    "confidence": "high",
    "not_established": "Whether the fall was caused by the 20mph zone rather than by a borough-wide trend or other confounding factors."
  },
  {
    "claim": "The drop in casualties inside the zone may reflect a broader downward trend rather than an effect of the speed limit, because casualties also fell i…
[
  {
    "claim": "Reported road casualties within the 20mph zone fell from 31 in the year before to 22 in the year after.",
    "supported_by": [
      "A"
    ],
    "contradicted_or_weakened_by": [],
    "confidence": "high",
    "not_established": "This before-after change alone does not settle whether the 20mph zone caused the reduction, whether the change is statistically significant, or whether it persisted beyond one year."
  },
  {
    "claim": "The casualty fall inside the zone cannot be confidently attributed to the 20mph limit on t…

Task by task

TaskClaude Opus 4.6GPT-5.5
Four numbers, one high street99
The trial that both worked and didn't99
Break the brief into answerable steps88
Corroboration that isn't99
The disagreement is definitional89
A forecast is not an outcome1010
The evidence table, as JSON59
Funded, and still the best data99.5
Write only the limits section109
Not answerable from what you have1010
The statistic and the doorstep109
Refuse the manufactured briefing59

Full receipts: Claude Opus 4.6, GPT-5.5 · judges gemini-3.1-pro-preview, gpt-5.6-terra, grok-4.5

Questions people ask

Which is better for multi-step research: Claude Opus 4.6 or GPT-5.5?

GPT-5.5 — it scored 91/100 against 85/100 on our 12-task multi-step research suite, winning 4 tasks to 2 with 6 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-5.5 vs GPT-5.6 Terra · Claude Opus 4.6 vs GPT-5.6 Terra · GPT-5.3-Codex vs GPT-5.5 · Claude Opus 4.6 vs GPT-5.3-Codex · Claude Sonnet 5 vs GPT-5.5 · Claude Opus 4.6 vs Claude Sonnet 5

Full ranking: Best AI for multi-step research · model pages: Claude Opus 4.6, GPT-5.5