Across 3 comparable benchmarks, Claude Sonnet 4.6 has better reported results on 3 and worse on 0.
Moderate evidence3 of 3 shared results countedHow we compare
Price basis: Listed rates vs standard rates. The price section below shows the applicable periods.
| Fact | Llama 4 Maverick Instruct | Claude Sonnet 4.6 |
|---|---|---|
| Context window | 1M tokens | 1M tokens |
| Input / 1M | $0.240 | $3.00 |
| Output / 1M | $0.970 | $15.00 |
| Blended (4:1) | $0.386 | $3.46 |
| Status | Available | Available |
| Released | April 5, 2025 | February 17, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 2 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Claude Sonnet 4.6 ahead on 1 of 1 counted
Claude Sonnet 4.6 ahead on 2 of 2 counted
No shared comparable results for Coding, Abstract reasoning, Mathematics, Computer & tool use, Research & search, Long context, Multimodal, Cybersecurity.
Published scores, with matching modes where available. Gaps show Llama 4 Maverick Instruct relative to Claude Sonnet 4.6. Reading the results
| Benchmark | Llama 4 Maverick Instruct | Claude Sonnet 4.6 | Gap |
|---|---|---|---|
| GPQA DiamondScientific Reasoning · Accuracy | 69.8Normal · no tools | 89.9≠Thinking · no tools | −20.1 pts#143 vs #52 of 200 |
| Creative WritingWriting | 858Normal · no tools | 1811Normal · no tools | 0.47×#109 vs #23 of 121 |
| SAGEService Workflows · Accuracy (%) | 35.7Unspecified Reasoning · tools | 46.6≠Max · tools | −10.9 pts#65 vs #34 of 82 |
Scientific Reasoning · Accuracy
Writing
Service Workflows · Accuracy (%)
A dash means no result is available.
| Benchmark | Llama 4 Maverick Instruct | Claude Sonnet 4.6 |
|---|---|---|
| CritPt | — | 3.1 |
| FrontierMath - Tier 4 | — | 8.3 |
| HLE | — | 49.0 |
| MMLU-Pro | 80.5 | — |
| SciCode | — | 50.1 |
| APEX-SWE | — | 34.5 |
| Code Migration | — | 39.9 |
| DeepSWE | — | 29.9 |
| FrontierCode 1.1 | — | 40.0 |
| LiveCodeBench | 43.4 | — |
| SWE-bench Verified | — | 79.6 |
| Terminal Bench 2.0 | — | 59.1 |
| Terminal Bench Hard | — | 53.0 |
| Terminal-Bench 4.0 | — | 3.0 |
| Vibe Code Bench v1.1 | — | 51.5 |
| APEX-Agents | — | 43.0 |
| MCP-Atlas | — | 69.5 |
| OSWorld 2.0 | — | 41.5 |
| OSWorld-Verified | — | 72.5 |
| Pinch Bench | — | 88.0 |
| PinchBench v2 | — | 62.7 |
| ExploitBench | — | 25.8 |
| ECI | — | 152 |
| LiveBench | — | 75.3 |
| LiveBench 2.0 | — | 65.1 |
| Vals Index | — | 50.6 |
| Context Arena | — | 82.8 |
| GDP.pdf | — | 15.8 |
| GeoBench ACW | — | 73.0 |
| MMMU-Pro | — | 75.6 |
| AA-AnalystAgent | — | 20.0 |
| AutomationBench | — | 5.3 |
| EMB (Excel Modeling) | — | 60.1 |
| Finance Agent v2 | — | 51.0 |
| GDPval-AA | — | 57.0 |
| Harvey Lab-AA | — | 86.0 |
| Harvey's Legal Agent Benchmark | — | 5.0 |
| Legal Research Bench | — | 38.5 |
| Public Benefits Bench v1.1 | — | 62.5 |
| Tax Agent Bench | — | 25.8 |
| τ²-Bench - Telecom | — | 97.9 |
| τ³-Banking | — | 34.4 |
| ARC-AGI-1 | — | 86.5 |
| ARC-AGI-2 | — | 60.4 |
| Vending-Bench 2 | — | 7204 |
| BrowseComp | — | 74.7 |
| MedCode | 36.5 | — |
| MedScribe | 54.2 | — |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
Llama 4 Maverick Instruct costs89%lessthan Claude Sonnet 4.6 per million tokens — 9× cheaper.Using listed rates vs standard rates at this token mix.
Llama 4 Maverick Instruct: Listed text rates; pricing tier not confirmed.
Claude Sonnet 4.6: Standard pricing. Anthropic official pricing (platform.claude.com/docs/en/about-claude/pricing) verified 2026-10-21; full 1M context at standard price
| Price / 1M tokens | Llama 4 Maverick Instruct | Claude Sonnet 4.6 | Ratio |
|---|---|---|---|
| Input | $0.24 | $3.00 | 0.08× |
| Output | $0.97 | $15.00 | 0.06× |
| Cached input | — | $0.30 | — |
| Cache write | — | — | — |
| Blended | $0.386 | $3.46 | 0.11× |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
| Benchmark | Llama 4 Maverick Instruct | Claude Sonnet 4.6 |
|---|---|---|
| ARC-AGI-1 | Not reported | |
| ARC-AGI-2 | Not reported | $2.6966 / task Average · ARC-AGI-2 Score: 60.4 Thinking High (With Tools) |
| AutomationBench | Not reported | $0.84 / task Average · Pass Rate: 5.0 Thinking High (With Tools) · zapier-private-heldout 1 more settings$0.77 / task Average · Pass Rate: 3.6 Thinking Medium (With Tools) · zapier-private-heldout |
| DeepSWE | Not reported | |
| FrontierCode 1.1 | Not reported | $2.8979 / task Average · Weighted rubric score: 24.3 Max (With Tools) · frontiercode-1-1-main $2.4401 / task Average · Weighted rubric score: 40.0 Max (With Tools) · frontiercode-1-1-extended $2.2694 / task Average · Weighted rubric score: 39.9 Thinking High (With Tools) · frontiercode-1-1-extended 5 more settings$2.6993 / task Average · Weighted rubric score: 23.5 Thinking High (With Tools) · frontiercode-1-1-main $1.4261 / task Average · Weighted rubric score: 30.4 Thinking Low (With Tools) · frontiercode-1-1-extended $1.6481 / task Average · Weighted rubric score: 15.0 Thinking Low (With Tools) · frontiercode-1-1-main $1.9375 / task Average · Weighted rubric score: 37.5 Thinking Medium (With Tools) · frontiercode-1-1-extended $2.3012 / task Average · Weighted rubric score: 21.1 Thinking Medium (With Tools) · frontiercode-1-1-main |
| LiveBench 2.0 | Not reported | $1.6841 / task Average · Overall score (equal-weight mean of 7 suite scores, 0-100): 65.1 Max (task-specific tools) |
| MedCode | Not reported | |
| MedScribe | Not reported | |
| SAGE | Not reported | |
| Tax Agent Bench | Not reported | $1.1935 / task Average · Accuracy (%, rubric × citation quality): 25.8 Unspecified Reasoning (With Tools) |
| Attribute | Llama 4 Maverick Instruct | Claude Sonnet 4.6 |
|---|---|---|
| Availability | Available | Available |
| Provider | Facebook AI Research Lab | Anthropic |
| Model type | Multimodal model | Chat model |
| First release | April 5, 2025 | February 17, 2026 |
| Context window | 1M tokens | 1M tokens |
| Max output | 4K tokens | 64K tokens |
| Total parameters | 400B | — |
| Architecture | Dense | Undisclosed |
| Documented capabilities | Multilingual | Reasoning, Multilingual |
| Knowledge cutoff | — | 2026-01 |
| Input modalities | Text, Image, Audio, Video | Text, Image |
| Output modalities | Text | Text |
| Weights | Open weights | Closed / API only |
| Licence | Llama4 License | — |
| Commercial use | Commercial use allowed | Proprietary |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used Llama 4 Maverick Instruct or Claude Sonnet 4.6? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.