Across 6 comparable benchmarks, Claude Opus 4.6 has better reported results on 6 and worse on 0. 1 further shared result is listed below, each with the reason it is not counted.
Moderate evidence6 of 7 shared results countedHow we compare
Price basis: Standard rates. The price section below shows the applicable periods.
| Fact | Claude Opus 4.6 | Llama 4 Scout |
|---|---|---|
| Context window | 1M tokens | 10M tokens |
| Input / 1M | $5.00 | $0.100 |
| Output / 1M | $25.00 | $0.300 |
| Blended (4:1) | $5.76 | $0.140 |
| Status | Available | Available |
| Released | February 5, 2026 | April 5, 2025 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 4 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Claude Opus 4.6 ahead on 1 of 1 counted
Claude Opus 4.6 ahead on 1 of 1 counted
Claude Opus 4.6 ahead on 1 of 1 counted
Claude Opus 4.6 ahead on 1 of 1 counted
Claude Opus 4.6 ahead on 1 of 1 counted
No fixed-scale average — see the rows in Benchmark results
No shared comparable results for Mathematics, Science & health, Research & search, Long context, Cybersecurity.
Published scores, with matching modes where available. Gaps show Claude Opus 4.6 relative to Llama 4 Scout. Reading the results
| Benchmark | Claude Opus 4.6 | Llama 4 Scout | Gap |
|---|---|---|---|
| Terminal Bench HardAgentic Development · Accuracy | 48.5Normal · tools | 1.5Normal · tools | +47.0 pts#14 vs #150 of 157 |
| ARC-AGI-1Abstract Generalization · Score (%) | 94.0Thinking High · no tools | 0.5≠Thinking · no tools | +93.5 pts#25 vs #87 of 87 |
| ARC-AGI-2Abstract Generalization · Score (% solved); cost per task (USD)Not counted · Speed and cost telemetry is reported, not scored | 69.2Thinking High · no tools | 0.0≠Thinking · no tools | —#29 vs #79 of 80 |
| PinchBench v2Tool Orchestration · Average score (%) | 69.9Reported best | 3.2Reported best | +66.7 pts#30 vs #51 of 51 |
| MMMU-ProVisual Understanding · Accuracy | 77.3Thinking · tools | 52.9≠Normal · no tools | +24.4 pts#49 vs #116 of 136 |
| τ³-BankingService Workflows · Score | 27.3Max · tools | 3.3≠Normal · tools | 8.28×#43 vs #119 of 120 |
| ECICapability Indices · ECI score (capability index, higher is better) | 155Reported best | 130Reported best | 1.20×#27 vs #118 of 168 |
Agentic Development · Accuracy
Abstract Generalization · Score (%)
Abstract Generalization · Score (% solved); cost per task (USD)
Not counted · Speed and cost telemetry is reported, not scored
Tool Orchestration · Average score (%)
Visual Understanding · Accuracy
Service Workflows · Score
Capability Indices · ECI score (capability index, higher is better)
A dash means no result is available.
| Benchmark | Claude Opus 4.6 | Llama 4 Scout |
|---|---|---|
| AIME 2026 | 96.7 | — |
| AIME2025 | 99.8 | — |
| CritPt | 12.6 | — |
| FrontierMath | 40.7 | — |
| FrontierMath - Tier 4 | 22.9 | — |
| FrontierMath Tier 4 v2 | 26.8 | — |
| FrontierMath v2 | 66.0 | — |
| GPQA Diamond | 91.3 | — |
| HLE | 53.0 | — |
| HLE-Verified | 46.8 | — |
| HMMT Feb 2026 | 96.2 | — |
| MATH | — | 50.3 |
| MATH-500 | 97.6 | — |
| MathArena Apex | 34.5 | — |
| MMLU | — | 79.6 |
| MMLU-Pro | — | 58.2 |
| Riemann-bench | 27.2 | — |
| SciCode | — | 21.3 |
| APEX-SWE | 41.8 | — |
| FrontierCode 1.1 | 43.7 | — |
| FrontierSWE v1 | 48.9 | — |
| GSO | 41.2 | — |
| HumanEval | 95.0 | — |
| LiveCodeBench | 76.0 | — |
| MBPP | — | 67.8 |
| SWE-bench Multilingual | 77.8 | — |
| SWE-Bench Pro - Commercial | 47.1 | — |
| SWE-Bench Pro - Public | 51.9 | — |
| SWE-bench Verified | 80.8 | — |
| Terminal Bench 2.0 | 65.4 | — |
| Vibe Code Bench v1.1 | 57.6 | — |
| WeirdML v2 | 78.0 | — |
| APEX-Agents | 46.3 | — |
| MCP-Atlas | 76.8 | — |
| OSWorld-Verified | 72.7 | — |
| Pinch Bench | 87.4 | — |
| LiveBench | 74.5 | — |
| Text Arena (Coding) | 1555 | — |
| Creative Writing | 1810 | — |
| Context Arena | 85.2 | — |
| EBR-bench | 12.7 | — |
| MMMU | — | 69.4 |
| SAGE | 51.6 | — |
| τ²-Bench | 91.9 | — |
| τ²-Bench - Telecom | 99.3 | — |
| ARC-AGI-3 | 0.51 | — |
| SimpleBench | 67.6 | — |
| Vending-Bench 2 | 8018 | — |
| BrowseComp | 84.0 | — |
| SimpleQA | 72.0 | — |
| MedCode | 49.1 | — |
| MedScribe | 86.7 | — |
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%
Claude Opus 4.6 costs4,014%morethan Llama 4 Scout per million tokens — 41.1× the price.Using standard rates at this token mix.
Claude Opus 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
Llama 4 Scout: Standard pricing. DeepInfra official models API (meta-llama/Llama-4-Scout-17B-16E-Instruct) verified 2026-11-13
| Price / 1M tokens | Claude Opus 4.6 | Llama 4 Scout | Ratio |
|---|---|---|---|
| Input | $5.00 | $0.10 | 50.0× |
| Output | $25.00 | $0.30 | 83.3× |
| Cached input | $0.50 | — | — |
| Cache write | — | — | — |
| Blended | $5.76 | $0.14 | 41.1× |
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.
Claude Opus 4.6 relative to Llama 4 Scout
No matching recorded settings for a cost summary.
Summary: 0 of 2 shared benchmarks have matching recorded settings and sources. The average is a geometric mean of 0 positive-cost ratios, one equal weight per benchmark. This benchmark set can include related tests and indexes; it is not a workload cost estimate.
Settings or sources differ or are not recorded; interpret the comparison with care.
Claude Opus 4.6
Llama 4 Scout
Settings or sources differ or are not recorded; interpret the comparison with care.
Claude Opus 4.6
Llama 4 Scout
| Benchmark | Claude Opus 4.6 | Llama 4 Scout |
|---|---|---|
| AIME 2026 | Not reported | |
| FrontierCode 1.1 | $3.1206 / task Average · Weighted rubric score: 42.9 Max (With Tools) · frontiercode-1-1-extended $3.7346 / task Average · Weighted rubric score: 26.9 Max (With Tools) · frontiercode-1-1-main $3.9796 / task Average · Weighted rubric score: 26.6 Thinking High (With Tools) · frontiercode-1-1-main 5 more settings$3.2978 / task Average · Weighted rubric score: 43.7 Thinking High (With Tools) · frontiercode-1-1-extended $1.8406 / task Average · Weighted rubric score: 32.9 Thinking Low (With Tools) · frontiercode-1-1-extended $2.101 / task Average · Weighted rubric score: 18.3 Thinking Low (With Tools) · frontiercode-1-1-main $2.3912 / task Average · Weighted rubric score: 38.6 Thinking Medium (With Tools) · frontiercode-1-1-extended $2.7941 / task Average · Weighted rubric score: 23.7 Thinking Medium (With Tools) · frontiercode-1-1-main | Not reported |
| Attribute | Claude Opus 4.6 | Llama 4 Scout |
|---|---|---|
| Availability | Available | Available |
| Provider | Anthropic | Facebook AI Research Lab |
| Model type | Reasoning model | Multimodal model |
| First release | February 5, 2026 | April 5, 2025 |
| Context window | 1M tokens | 10M tokens |
| Max output | 64K tokens | 4K tokens |
| Total parameters | — | 109B |
| Architecture | Undisclosed | Dense |
| Documented capabilities | Reasoning, Multilingual | Multilingual |
| Knowledge cutoff | 2025-05 | — |
| Input modalities | Text, Image | Text, Image, Audio, Video |
| Output modalities | Text | Text |
| Weights | Closed / API only | Open weights |
| Licence | — | Llama4 License |
| Commercial use | Proprietary | Commercial use allowed |
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 Claude Opus 4.6 or Llama 4 Scout? 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.