Compare / head-to-head
Claude Sonnet 5.5vs
Inkling
Claude Sonnet 5.5 leads 20 of 20 shared benchmarks. Inkling is 2.4x cheaper per token. Both offer a 1M-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
20 – 0
Claude Sonnet 5.5 leads
Cheaper per token
Inkling
2.4x cheaper, input + output
Larger context
Tie
both 1M tokens
Providers
2 providers
Anthropic · Thinking Machines Lab
Claude Sonnet 5.5
Anthropic · released 2026-09-28
textvision
Quality
Benchmark matrix
20 shared · 9 only Claude Sonnet 5.5 · 18 only Inkling| Benchmark | Claude Sonnet 5.5 | Inkling | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 20 | ||||
| GPQA Diamond | 95.6% ↗epoch run | 88.3% ↗epoch run | +7.3 pt | Claude Sonnet 5.5 |
| LMArena Elo | 1471 ↗ | 1441.4 ↗ | +29.6 | Claude Sonnet 5.5 |
| APEX-Agents (Mercor) | 75.5% ↗ | 33.8% ↗ | +41.7 pt | Claude Sonnet 5.5 |
| FrontierMath Tier 4 v2 (Epoch AI run) | 80.5% ↗epoch run | 4.9% ↗epoch run | +75.6 pt | Claude Sonnet 5.5 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 88.8% ↗epoch run | 33.3% ↗epoch run | +55.5 pt | Claude Sonnet 5.5 |
| FrontierSWE V2 (Proximal Labs) | 61.9% ↗ | 4.1% ↗ | +57.8 pt | Claude Sonnet 5.5 |
| LiveBench Agentic Coding (LiveBench) | 56.3% ↗ | 49.4% ↗ | +6.9 pt | Claude Sonnet 5.5 |
| LiveBench Coding (LiveBench) | 91.4% ↗ | 71% ↗ | +20.4 pt | Claude Sonnet 5.5 |
| LiveBench Data Analysis (LiveBench) | 78.6% ↗ | 72.8% ↗ | +5.8 pt | Claude Sonnet 5.5 |
| LiveBench Instruction Following (LiveBench) | 70.5% ↗ | 70.1% ↗ | +0.4 pt | Claude Sonnet 5.5 |
| LiveBench Language (LiveBench) | 83.4% ↗ | 73.5% ↗ | +9.9 pt | Claude Sonnet 5.5 |
| LiveBench Mathematics (LiveBench) | 96.7% ↗ | 88.4% ↗ | +8.3 pt | Claude Sonnet 5.5 |
| LiveBench Reasoning (LiveBench) | 91.6% ↗ | 78.3% ↗ | +13.3 pt | Claude Sonnet 5.5 |
| LMArena Agent (LMArena) | 0.1252 ↗ | -0.1086 ↗ | +0.2 | Claude Sonnet 5.5 |
| LMArena WebDev (LMArena) | 1786.3 ↗ | 1412.6 ↗ | +373.7 | Claude Sonnet 5.5 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 100% ↗epoch run | 88.9% ↗epoch run | +11.1 pt | Claude Sonnet 5.5 |
| SAGE (Vals AI) | 51.8% ↗ | 36.6% ↗ | +15.2 pt | Claude Sonnet 5.5 |
| SimpleBench (SimpleBench) | 75.9% ↗ | 50% ↗ | +25.9 pt | Claude Sonnet 5.5 |
| SimpleQA Verified | 46.5% ↗epoch run | 43.9% ↗ | +2.6 pt | Claude Sonnet 5.5 |
| Terminal-Bench 4.0 (Vals AI) | 64.1% ↗ | 0.5% ↗ | +63.6 pt | Claude Sonnet 5.5 |
| Only Claude Sonnet 5.5 reports · 9 | ||||
| Chartography (no tools) | 61.6% ↗ | not reported | — | — |
| CursorBench 4.0 | 55.5% ↗ | not reported | — | — |
| FrontierCode v1.1 (Main) | 46.2% ↗ | not reported | — | — |
| Furniture Assembly (Epoch AI run) | 75% ↗epoch run | not reported | — | — |
| Humanity's Last Exam (with tools) | 64.5% ↗ | not reported | — | — |
| LMArena Vision (LMArena) | 1268.3 ↗ | not reported | — | — |
| Mystery Game Puzzles (Epoch AI run) | 65% ↗epoch run | not reported | — | — |
| OSWorld 2.1 (partial) | 80.1% ↗ | not reported | — | — |
| Terminal-Bench 4.0 | 70.6% ↗ | not reported | — | — |
| Only Inkling reports · 18 | ||||
| SWE-bench Verified | not reported | 77.6% ↗ | — | — |
| AIME 2026 | not reported | 97.1% ↗ | — | — |
| Audio MC | not reported | 56.6% ↗ | — | — |
| BrowseComp (w/ ctx management) | not reported | 77.1% ↗ | — | — |
| CharXiv RQ | not reported | 78.1% ↗ | — | — |
| CharXiv RQ (with python) | not reported | 82% ↗ | — | — |
| Chess Puzzles (Epoch AI run) | not reported | 21% ↗epoch run | — | — |
| Global-MMLU-Lite | not reported | 88.7% ↗ | — | — |
| IFBench | not reported | 79.8% ↗ | — | — |
| MCP Atlas | not reported | 76% ↗ | — | — |
| MMAU | not reported | 77.2% ↗ | — | — |
| SWE-bench Pro (public) | not reported | 54.3% ↗ | — | — |
| tau2-bench Banking Knowledge (Sierra) | not reported | 25% ↗ | — | — |
| Terminal-Bench 2.1 (best harness) | not reported | 63.8% ↗ | — | — |
| Toolathlon Verified | not reported | 45.5% ↗ | — | — |
| Toolathlon-Verified (HKUST) | not reported | 45.5% ↗ | — | — |
| VoiceBench | not reported | 91.4% ↗ | — | — |
| WeirdML (Håvard Tveit Ihle) | not reported | 32.3% ↗ | — | — |
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 Claude Sonnet 5.5 minus Inkling 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 | Claude Sonnet 5.5 | Inkling | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1M tokens | Tie |
| Max output | 128K tokens | — | — |
| Input price / 1M | $2 ↗ | $1 ↗ | Inkling |
| Output price / 1M | $10 ↗ | $4.05 ↗ | Inkling |
| Cached input / 1M | $0.2 ↗ | $0.17 ↗ | Inkling |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $12 | $5.05 | Inkling |
| Modalities | text · vision | text · vision · audio | Inkling |
| Released | 2026-09-28 | 2026-07-15 | — |
| Cited benchmark scores | 29 | 39 | — |
Reliability
Provider status
Live from /statusMore matchups
Claude Sonnet 5.5 vs …
Models sharing the most benchmarksMore matchups
Inkling vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Sonnet 5.5 and Inkling on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.