Compare / head-to-head
Inklingvs
MAI-Thinking-1
Inkling leads 5 of 5 shared benchmarks. Inkling has the larger context window (1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
5 – 0
Inkling leads
Cheaper per token
—
list price, input + output
Larger context
Inkling
1M tokens
Providers
2 providers
Thinking Machines Lab · Microsoft
Inkling
Thinking Machines Lab · released 2026-07-15
textvisionaudio
MAI-Thinking-1
Microsoft · released 2026-08-12
text
- Context
- 256K
- Max out
- 64K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 15 · 7 core
Quality
Benchmark matrix
5 shared · 33 only Inkling · 10 only MAI-Thinking-1| Benchmark | Inkling | MAI-Thinking-1 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 5 | ||||
| SWE-bench Verified | 77.6% ↗ | 73.5% ↗ | +4.1 pt | Inkling |
| GPQA Diamond | 88.3% ↗epoch run | 84.2% ↗ | +4.1 pt | Inkling |
| AIME 2026 | 97.1% ↗ | 94.5% ↗ | +2.6 pt | Inkling |
| IFBench | 79.8% ↗ | 69% ↗ | +10.8 pt | Inkling |
| SimpleQA Verified | 43.9% ↗ | 31% ↗ | +12.9 pt | Inkling |
| Only Inkling reports · 33 | ||||
| LMArena Elo | 1441.4 ↗ | not reported | — | — |
| APEX-Agents (Mercor) | 33.8% ↗ | not reported | — | — |
| Audio MC | 56.6% ↗ | not reported | — | — |
| BrowseComp (w/ ctx management) | 77.1% ↗ | not reported | — | — |
| CharXiv RQ | 78.1% ↗ | not reported | — | — |
| CharXiv RQ (with python) | 82% ↗ | not reported | — | — |
| Chess Puzzles (Epoch AI run) | 21% ↗epoch run | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 4.9% ↗epoch run | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 33.3% ↗epoch run | not reported | — | — |
| FrontierSWE V2 (Proximal Labs) | 4.1% ↗ | not reported | — | — |
| Global-MMLU-Lite | 88.7% ↗ | not reported | — | — |
| LiveBench Agentic Coding (LiveBench) | 49.4% ↗ | not reported | — | — |
| LiveBench Coding (LiveBench) | 71% ↗ | not reported | — | — |
| LiveBench Data Analysis (LiveBench) | 72.8% ↗ | not reported | — | — |
| LiveBench Instruction Following (LiveBench) | 70.1% ↗ | not reported | — | — |
| LiveBench Language (LiveBench) | 73.5% ↗ | not reported | — | — |
| LiveBench Mathematics (LiveBench) | 88.4% ↗ | not reported | — | — |
| LiveBench Reasoning (LiveBench) | 78.3% ↗ | not reported | — | — |
| LMArena Agent (LMArena) | -0.1086 ↗ | not reported | — | — |
| LMArena WebDev (LMArena) | 1412.6 ↗ | not reported | — | — |
| MCP Atlas | 76% ↗ | not reported | — | — |
| MMAU | 77.2% ↗ | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 88.9% ↗epoch run | not reported | — | — |
| SAGE (Vals AI) | 36.6% ↗ | not reported | — | — |
| SimpleBench (SimpleBench) | 50% ↗ | not reported | — | — |
| SWE-bench Pro (public) | 54.3% ↗ | not reported | — | — |
| tau2-bench Banking Knowledge (Sierra) | 25% ↗ | not reported | — | — |
| Terminal-Bench 2.1 (best harness) | 63.8% ↗ | not reported | — | — |
| Terminal-Bench 4.0 (Vals AI) | 0.5% ↗ | not reported | — | — |
| Toolathlon Verified | 45.5% ↗ | not reported | — | — |
| Toolathlon-Verified (HKUST) | 45.5% ↗ | not reported | — | — |
| VoiceBench | 91.4% ↗ | not reported | — | — |
| WeirdML (Håvard Tveit Ihle) | 32.3% ↗ | not reported | — | — |
| Only MAI-Thinking-1 reports · 10 | ||||
| MMLU-Pro | not reported | 85% ↗ | — | — |
| AIME 2025 | not reported | 97% ↗ | — | — |
| AdvancedIF | not reported | 85% ↗ | — | — |
| BFCL v3 | not reported | 72% ↗ | — | — |
| GraphWalks (<=128K) | not reported | 90% ↗ | — | — |
| HMMT February 2026 | not reported | 84.9% ↗ | — | — |
| LiveCodeBench v6 | not reported | 87.7% ↗ | — | — |
| MultiChallenge | not reported | 53% ↗ | — | — |
| SWE-bench Pro | not reported | 52.8% ↗ | — | — |
| Terminal-Bench 2.0 | not reported | 46% ↗ | — | — |
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 Inkling minus MAI-Thinking-1 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 | Inkling | MAI-Thinking-1 | Edge |
|---|---|---|---|
| Context window | 1M tokens | 256K tokens | Inkling |
| Max output | — | 64K tokens | — |
| Input price / 1M | $1 ↗ | — | — |
| Output price / 1M | $4.05 ↗ | — | — |
| Cached input / 1M | $0.17 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $5.05 | — | — |
| Modalities | text · vision · audio | text | Inkling |
| Released | 2026-07-15 | 2026-08-12 | — |
| Cited benchmark scores | 39 | 15 | — |
Reliability
Provider status
Live from /statusMore matchups
Inkling vs …
Models sharing the most benchmarksMore matchups
MAI-Thinking-1 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Inkling and MAI-Thinking-1 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.