Grok 4.5 vs Kimi K3 for multi-step research
Kimi K3 wins, 88–85
Same 12 multi-step research tasks, marked blind by three rival labs. Kimi K3 took 7 tasks, Grok 4.5 took 3, 2 tied. Tested 18 Aug 2026.
Where they differed most
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).
[
{
"claim": "Road casualties inside the 20mph zone were lower in the year after introduction than in the year before.",
"supported_by": ["A"],
"contradicted_or_weakened_by": ["B"],
"confidence": "high",
"not_established": "Whether the fall was caused by the 20mph zone rather than wider trends, regression to the mean, or other concurrent factors."
},
{
"claim": "Casualty reductions occurred borough-wide over the same period, including on streets with no speed-limit change.",
"supported_by": ["B"],
"contradi…[
{
"claim": "Reported road casualties within the 20mph zone fell from 31 in the year before its introduction to 22 in the year after.",
"supported_by": ["A"],
"contradicted_or_weakened_by": [],
"confidence": "high",
"not_established": "Whether the fall is statistically significant, whether it reflects changes in traffic volume or collision reporting rather than genuine risk reduction, the severity of the casualties, and whether the zone caused the fall."
},
{
"claim": "Casualties also fell across the whole borough…Task by task
| Task | Grok 4.5 | Kimi K3 |
|---|---|---|
| Four numbers, one high street | 8 | 9 |
| The trial that both worked and didn't | 8 | 9 |
| Break the brief into answerable steps | 9 | 9 |
| Corroboration that isn't | 8 | 9 |
| The disagreement is definitional | 7 | 8 |
| A forecast is not an outcome | 8 | 9 |
| The evidence table, as JSON | 10 | 8 |
| Funded, and still the best data | 8 | 9 |
| Write only the limits section | 9 | 8 |
| Not answerable from what you have | 9 | 9 |
| The statistic and the doorstep | 8 | 9 |
| Refuse the manufactured briefing | 10 | 9 |
Full receipts: Grok 4.5, Kimi K3 · judges claude-sonnet-5, gemini-3.1-pro-preview, gpt-5.6-terra
Questions people ask
Which is better for multi-step research: Grok 4.5 or Kimi K3?
Kimi K3 — it scored 88/100 against 85/100 on our 12-task multi-step research suite, winning 7 tasks to 3 with 2 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: Claude Sonnet 5 vs Kimi K3 · Claude Sonnet 5 vs Grok 4.5 · GPT-5.5 vs Kimi K3 · GPT-5.5 vs Grok 4.5 · GPT-5.6 Sol vs Kimi K3 · GPT-5.6 Sol vs Grok 4.5
Full ranking: Best AI for multi-step research · model pages: Grok 4.5, Kimi K3