Compare / head-to-head
MAI-Thinking-1vsStep 3.5 Flash
Step 3.5 Flash leads 4 of 5 shared benchmarks. Both offer a 256K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
1 – 4
Step 3.5 Flash leads
Cheaper per token
—
list price, input + output
Larger context
Tie
both 256K tokens
Provider uptime (30d)
— · —
Microsoft · StepFun
MAI-Thinking-1
Microsoft · released 2026-08-12
text
- Context
- 256K
- Max out
- 64K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 15 · 7 core
Step 3.5 Flash
StepFun · released 2026-02-12
text
- Context
- 256K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 18 · 5 core
Quality
Benchmark matrix
5 shared · 10 only MAI-Thinking-1 · 12 only Step 3.5 Flash| Benchmark | MAI-Thinking-1 | Step 3.5 Flash | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 5 | ||||
| SWE-bench Verified | 73.5% ↗ | 74.4% ↗ | -0.9 pt | Step 3.5 Flash |
| AIME 2025 | 97% ↗ | 97.3% ↗ | -0.3 pt | Step 3.5 Flash |
| AIME 2026 | 94.5% ↗ | 96.7% ↗matharena | -2.2 pt | Step 3.5 Flash |
| LiveCodeBench v6 | 87.7% ↗ | 86.4% ↗ | +1.3 pt | MAI-Thinking-1 |
| Terminal-Bench 2.0 | 46% ↗ | 51% ↗ | -5 pt | Step 3.5 Flash |
| Only MAI-Thinking-1 reports · 10 | ||||
| GPQA Diamond | 84.2% ↗ | not reported | — | — |
| MMLU-Pro | 85% ↗ | not reported | — | — |
| AdvancedIF | 85% ↗ | not reported | — | — |
| BFCL v3 | 72% ↗ | not reported | — | — |
| GraphWalks (<=128K) | 90% ↗ | not reported | — | — |
| HMMT February 2026 | 84.9% ↗ | not reported | — | — |
| IFBench | 69% ↗ | not reported | — | — |
| MultiChallenge | 53% ↗ | not reported | — | — |
| SimpleQA Verified | 31% ↗ | not reported | — | — |
| SWE-bench Pro | 52.8% ↗ | not reported | — | — |
| Only Step 3.5 Flash reports · 12 | ||||
| LMArena Elo | not reported | 1403.7 ↗ | — | — |
| BrowseComp | not reported | 51.6% ↗ | — | — |
| BrowseComp (with context manager) | not reported | 69% ↗ | — | — |
| BrowseComp-ZH | not reported | 66.9% ↗ | — | — |
| BrowseComp-ZH (with context manager) | not reported | 73.7% ↗ | — | — |
| GAIA (no file) | not reported | 84.5% ↗ | — | — |
| HMMT 2025 (Feb/Nov average) | not reported | 96.2% ↗ | — | — |
| IMOAnswerBench | not reported | 85.4% ↗ | — | — |
| ResearchRubrics | not reported | 65.3% ↗ | — | — |
| Tau2-Bench | not reported | 88.2% ↗ | — | — |
| xbench-DeepSearch 2025.05 | not reported | 83.7% ↗ | — | — |
| xbench-DeepSearch 2025.10 | not reported | 56.3% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is MAI-Thinking-1 minus Step 3.5 Flash in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | MAI-Thinking-1 | Step 3.5 Flash | Edge |
|---|---|---|---|
| Context window | 256K tokens | 256K tokens | Tie |
| Max output | 64K tokens | — | — |
| Input price / 1M | — | — | — |
| Output price / 1M | — | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | — | — |
| Modalities | text | text | Tie |
| Released | 2026-08-12 | 2026-02-12 | — |
| Cited benchmark scores | 15 | 18 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
MAI-Thinking-1 vs …
Models sharing the most benchmarksMore matchups
Step 3.5 Flash vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run MAI-Thinking-1 and Step 3.5 Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.