Compare / head-to-head
Inkling-Smallvs
Muse Spark 1.3
Muse Spark 1.3 leads 10 of 10 shared benchmarks. Inkling-Small is 3.7x cheaper per token. Muse Spark 1.3 has the larger context window (1.0M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 10
Muse Spark 1.3 leads
Cheaper per token
Inkling-Small
3.7x cheaper, input + output
Larger context
Muse Spark 1.3
1.0M tokens
Providers
2 providers
Thinking Machines Lab · Meta
Inkling-Small
Thinking Machines Lab · released 2026-07-30
textvisionaudio
Muse Spark 1.3
Meta · released 2026-09-02
textvisionvideo
Quality
Benchmark matrix
10 shared · 18 only Inkling-Small · 19 only Muse Spark 1.3| Benchmark | Inkling-Small | Muse Spark 1.3 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 10 | ||||
| LMArena Elo | 1405.2 ↗ | 1494.3 ↗ | -89.1 | Muse Spark 1.3 |
| Chess Puzzles (Epoch AI run) | 18% ↗epoch run | 38% ↗epoch run | -20 pt | Muse Spark 1.3 |
| FrontierMath Tier 4 v2 (Epoch AI run) | 17.1% ↗epoch run | 46.3% ↗epoch run | -29.2 pt | Muse Spark 1.3 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 46.3% ↗epoch run | 74.4% ↗epoch run | -28.1 pt | Muse Spark 1.3 |
| LMArena Agent (LMArena) | -0.1033 ↗ | 0.04 ↗ | -0.1 | Muse Spark 1.3 |
| LMArena Vision (LMArena) | 1206.3 ↗ | 1290.2 ↗ | -83.9 | Muse Spark 1.3 |
| LMArena WebDev (LMArena) | 1408.2 ↗ | 1656.6 ↗ | -248.4 | Muse Spark 1.3 |
| Mystery Game Puzzles (Epoch AI run) | 6% ↗epoch run | 25% ↗epoch run | -19 pt | Muse Spark 1.3 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 90% ↗epoch run | 99.2% ↗epoch run | -9.2 pt | Muse Spark 1.3 |
| Terminal-Bench 4.0 (Vals AI) | 0% ↗ | 24.7% ↗ | -24.7 pt | Muse Spark 1.3 |
| Only Inkling-Small reports · 18 | ||||
| SWE-bench Verified | 80.2% ↗ | not reported | — | — |
| GPQA Diamond | 88.5% ↗epoch run | not reported | — | — |
| AIME 2026 | 95.5% ↗ | not reported | — | — |
| ARC-AGI-1 | 84% ↗ | not reported | — | — |
| ARC-AGI-2 | 40.1% ↗ | not reported | — | — |
| BrowseComp (with context management) | 77.4% ↗ | not reported | — | — |
| CharXiv RQ | 77.4% ↗ | not reported | — | — |
| CharXiv RQ (with python) | 81.3% ↗ | not reported | — | — |
| HMMT Feb 2026 | 90.2% ↗ | not reported | — | — |
| IFBench | 82.2% ↗ | not reported | — | — |
| MCP Atlas (all) | 79.2% ↗ | not reported | — | — |
| MMAU | 77% ↗ | not reported | — | — |
| SAGE (Vals AI) | 32.7% ↗ | not reported | — | — |
| SimpleQA Verified | 20.6% ↗ | not reported | — | — |
| SWE-bench Pro (public) | 55.9% ↗ | not reported | — | — |
| Terminal-Bench 2.1 (best harness) | 64.7% ↗ | not reported | — | — |
| Toolathlon Verified | 54.4% ↗ | not reported | — | — |
| Toolathlon-Verified (HKUST) | 54.4% ↗ | not reported | — | — |
| Only Muse Spark 1.3 reports · 19 | ||||
| APEX-Agents (Mercor) | not reported | 57.8% ↗ | — | — |
| AutomationBench | not reported | 49.6% ↗ | — | — |
| DeepSearchQA | not reported | 90.3% ↗ | — | — |
| DeepSWE v1.1 | not reported | 75.4% ↗ | — | — |
| GDPval-AA v2 | not reported | 1754 ↗ | — | — |
| JobBench | not reported | 64.9% ↗ | — | — |
| LiveBench Agentic Coding (LiveBench) | not reported | 64.1% ↗ | — | — |
| LiveBench Coding (LiveBench) | not reported | 81.1% ↗ | — | — |
| LiveBench Data Analysis (LiveBench) | not reported | 79.6% ↗ | — | — |
| LiveBench Instruction Following (LiveBench) | not reported | 78% ↗ | — | — |
| LiveBench Language (LiveBench) | not reported | 82.8% ↗ | — | — |
| LiveBench Mathematics (LiveBench) | not reported | 95.9% ↗ | — | — |
| LiveBench Reasoning (LiveBench) | not reported | 89.7% ↗ | — | — |
| MRCR 256K-512K | not reported | 98.5% ↗ | — | — |
| MRCR 512K-1M | not reported | 98.1% ↗ | — | — |
| OSWorld 2.0 (partial) | not reported | 66.9% ↗ | — | — |
| SimpleBench (SimpleBench) | not reported | 81.8% ↗ | — | — |
| SWE-Atlas Codebase QnA | not reported | 59.4% ↗ | — | — |
| Terminal-Bench 2.1 | not reported | 88.8% ↗ | — | — |
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-Small minus Muse Spark 1.3 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-Small | Muse Spark 1.3 | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1.0M tokens | Muse Spark 1.3 |
| Max output | — | — | — |
| Input price / 1M | $0.3 ↗ | $1.25 ↗ | Inkling-Small |
| Output price / 1M | $1.2 ↗ | $4.25 ↗ | Inkling-Small |
| Cached input / 1M | $0.06 ↗ | $0.15 ↗ | Inkling-Small |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $1.5 | $5.5 | Inkling-Small |
| Modalities | text · vision · audio | text · vision · video | Tie |
| Released | 2026-07-30 | 2026-09-02 | — |
| Cited benchmark scores | 29 | 29 | — |
Reliability
Provider status
Live from /statusMore matchups
Inkling-Small vs …
Models sharing the most benchmarksMore matchups
Muse Spark 1.3 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Inkling-Small and Muse Spark 1.3 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.