Compare / head-to-head
Claude Opus 4.8vs
Inkling
Claude Opus 4.8 leads 24 of 25 shared benchmarks. Inkling is 5.9x 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
24 – 1
Claude Opus 4.8 leads
Cheaper per token
Inkling
5.9x cheaper, input + output
Larger context
Tie
both 1M tokens
Providers
2 providers
Anthropic · Thinking Machines Lab
Claude Opus 4.8
Anthropic · released 2026-05-28
textvision
Quality
Benchmark matrix
25 shared · 15 only Claude Opus 4.8 · 13 only Inkling| Benchmark | Claude Opus 4.8 | Inkling | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 25 | ||||
| SWE-bench Verified | 88.6% ↗ | 77.6% ↗ | +11 pt | Claude Opus 4.8 |
| GPQA Diamond | 93.6% ↗ | 88.3% ↗epoch run | +5.3 pt | Claude Opus 4.8 |
| AIME 2026 | 100% ↗matharena ⚠ | 97.1% ↗ | +2.9 pt | Claude Opus 4.8 |
| LMArena Elo | 1452.7 ↗ | 1441.4 ↗ | +11.3 | Claude Opus 4.8 |
| APEX-Agents (Mercor) | 48.9% ↗ | 33.8% ↗ | +15.1 pt | Claude Opus 4.8 |
| Chess Puzzles (Epoch AI run) | 34% ↗epoch run | 21% ↗epoch run | +13 pt | Claude Opus 4.8 |
| FrontierMath Tier 4 v2 (Epoch AI run) | 56.1% ↗epoch run | 4.9% ↗epoch run | +51.2 pt | Claude Opus 4.8 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 80% ↗epoch run | 33.3% ↗epoch run | +46.7 pt | Claude Opus 4.8 |
| LiveBench Agentic Coding (LiveBench) | 50.5% ↗ | 49.4% ↗ | +1.1 pt | Claude Opus 4.8 |
| LiveBench Coding (LiveBench) | 81.8% ↗ | 71% ↗ | +10.8 pt | Claude Opus 4.8 |
| LiveBench Data Analysis (LiveBench) | 66% ↗ | 72.8% ↗ | -6.8 pt | Inkling |
| LiveBench Instruction Following (LiveBench) | 72% ↗ | 70.1% ↗ | +1.9 pt | Claude Opus 4.8 |
| LiveBench Language (LiveBench) | 79.7% ↗ | 73.5% ↗ | +6.2 pt | Claude Opus 4.8 |
| LiveBench Mathematics (LiveBench) | 94.3% ↗ | 88.4% ↗ | +5.9 pt | Claude Opus 4.8 |
| LiveBench Reasoning (LiveBench) | 89.2% ↗ | 78.3% ↗ | +10.9 pt | Claude Opus 4.8 |
| LMArena Agent (LMArena) | 0.0664 ↗ | -0.1086 ↗ | +0.2 | Claude Opus 4.8 |
| LMArena WebDev (LMArena) | 1555.5 ↗ | 1412.6 ↗ | +142.9 | Claude Opus 4.8 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 98.3% ↗epoch run | 88.9% ↗epoch run | +9.4 pt | Claude Opus 4.8 |
| SAGE (Vals AI) | 54.8% ↗ | 36.6% ↗ | +18.2 pt | Claude Opus 4.8 |
| SimpleBench (SimpleBench) | 64.8% ↗ | 50% ↗ | +14.8 pt | Claude Opus 4.8 |
| SimpleQA Verified | 53% ↗epoch run | 43.9% ↗ | +9.1 pt | Claude Opus 4.8 |
| tau2-bench Banking Knowledge (Sierra) | 39.7% ↗ | 25% ↗ | +14.7 pt | Claude Opus 4.8 |
| Terminal-Bench 4.0 (Vals AI) | 23.2% ↗ | 0.5% ↗ | +22.7 pt | Claude Opus 4.8 |
| Toolathlon-Verified (HKUST) | 76.2% ↗ | 45.5% ↗ | +30.7 pt | Claude Opus 4.8 |
| WeirdML (Håvard Tveit Ihle) | 82.9% ↗ | 32.3% ↗ | +50.6 pt | Claude Opus 4.8 |
| Only Claude Opus 4.8 reports · 15 | ||||
| Humanity's Last Exam (no tools) | 49.8% ↗ | not reported | — | — |
| BrowseComp | 84.3% ↗ | not reported | — | — |
| DeepSWE v1.1 (Datacurve) | 59% ↗ | not reported | — | — |
| EBR-bench (Epoch AI run) | 28.6% ↗epoch run | not reported | — | — |
| Furniture Assembly (Epoch AI run) | 42.5% ↗epoch run | not reported | — | — |
| GSO Opt@1 (GSO) | 47.1% ↗ | not reported | — | — |
| Humanity's Last Exam (with tools) | 57.9% ↗ | not reported | — | — |
| LMArena Vision (LMArena) | 1286.4 ↗ | not reported | — | — |
| Mystery Game Puzzles (Epoch AI run) | 36% ↗epoch run | not reported | — | — |
| OSWorld-Verified | 83.4% ↗ | not reported | — | — |
| SWE-bench Multilingual | 84.4% ↗ | not reported | — | — |
| SWE-bench Multimodal | 38.4% ↗ | not reported | — | — |
| SWE-Bench Pro | 69.2% ↗ | not reported | — | — |
| Terminal-Bench 2.1 | 74.6% ↗ | not reported | — | — |
| Vending-Bench 2 (Andon Labs) | 5787.43 ↗ | not reported | — | — |
| Only Inkling reports · 13 | ||||
| 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% ↗ | — | — |
| FrontierSWE V2 (Proximal Labs) | not reported | 4.1% ↗ | — | — |
| 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% ↗ | — | — |
| Terminal-Bench 2.1 (best harness) | not reported | 63.8% ↗ | — | — |
| Toolathlon Verified | not reported | 45.5% ↗ | — | — |
| VoiceBench | not reported | 91.4% ↗ | — | — |
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 Opus 4.8 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 Opus 4.8 | Inkling | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1M tokens | Tie |
| Max output | 128K tokens | — | — |
| Input price / 1M | $5 ↗ | $1 ↗ | Inkling |
| Output price / 1M | $25 ↗ | $4.05 ↗ | Inkling |
| Cached input / 1M | $0.5 ↗ | $0.17 ↗ | Inkling |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $30 | $5.05 | Inkling |
| Modalities | text · vision | text · vision · audio | Inkling |
| Released | 2026-05-28 | 2026-07-15 | — |
| Cited benchmark scores | 47 | 39 | — |
Reliability
Provider status
Live from /statusMore matchups
Claude Opus 4.8 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 Opus 4.8 and Inkling on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.