Model comparison
Claude Opus 4.5 Thinking vs Claude Opus 4.6
Head-to-head evidence from 14 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Claude Opus 4.5 Thinking #69 (Estimated); Claude Opus 4.6 #16 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Claude Opus 4.5 Thinking and Claude Opus 4.6 share 14 comparable benchmark results. 0 of 8 categories are comparable. 2 results are unique to Claude Opus 4.5 Thinking; 32 to Claude Opus 4.6.
Updated July 23, 2026- Shared results
- 14
- Claude Opus 4.5 Thinking only
- 2
- Claude Opus 4.6 only
- 32
- Comparable categories
- 0 / 8
Benchmark data for Claude Opus 4.5 Thinking and Claude Opus 4.6 is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 14 shared benchmark results across 6 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.
Claude Opus 4.6 has the larger context window at 1M, compared with 200K for Claude Opus 4.5 Thinking.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Claude Opus 4.5 Thinking | Δ | Claude Opus 4.6 |
|---|---|---|---|
| Agentic | Claude Opus 4.5 ThinkingNot measured | MarginNo overlap | Claude Opus 4.673.0 |
| Coding | Claude Opus 4.5 ThinkingNot measured | MarginNo overlap | Claude Opus 4.668.1 |
| Knowledge | Claude Opus 4.5 ThinkingNot measured | MarginNo overlap | Claude Opus 4.669.1 |
| Math | Claude Opus 4.5 ThinkingNot measured | MarginNo overlap | Claude Opus 4.636.3 |
| Multimodal | Claude Opus 4.5 ThinkingNot measured | MarginNo overlap | Claude Opus 4.677.3 |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Claude Opus 4.5 Thinking | Claude Opus 4.6 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Claude Opus 4.5 ThinkingNot available | Claude Opus 4.6$5 input / $25 output | A complete price comparison is not available. |
| Generation speedtokens per second | Claude Opus 4.5 ThinkingNot available | Claude Opus 4.640 tok/s | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Claude Opus 4.5 ThinkingNot available | Claude Opus 4.61.78 s | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Claude Opus 4.5 Thinking200K | Claude Opus 4.61M | Claude Opus 4.6 lists the larger context window. |
Benchmark Deep Dive
Agentic10 benchmarks
| Benchmark | Claude Opus 4.5 Thinking | Claude Opus 4.6 | Result |
|---|---|---|---|
| τ²-bench resultsSource | 89.5% | 84.8% | Claude Opus 4.5 Thinking leads |
| Terminal-Bench 2.0Source | — | 65.4% | Not comparable |
| BrowseCompSource | — | 83.7% | Not comparable |
| OSWorld-VerifiedSource | — | 72.7% | Not comparable |
| Claw-EvalSource | — | 70.4% | Not comparable |
| DeepSearchQASource | — | 73.7% | Not comparable |
| CyberGymSource | — | 66.6% | Not comparable |
| Gert LabsSource | — | 61.85% | Not comparable |
| ResearchClawBenchSource | — | 19.9% | Not comparable |
| JobBenchSource | — | 36.7% | Not comparable |
Coding9 benchmarks
| Benchmark | Claude Opus 4.5 Thinking | Claude Opus 4.6 | Result |
|---|---|---|---|
| Vibe Code BenchSource | 20.63% | 57.57% | Claude Opus 4.6 leads |
| AA-SciCodeSource | 49.5% | 45.7% | Claude Opus 4.5 Thinking leads |
| SWE-bench VerifiedSource | — | 80.8% | Not comparable |
| SWE-bench Verified*Source | — | 75.6% | Not comparable |
| LiveCodeBench ProSource | — | 70.7% | Not comparable |
| SWE-bench ProSource | — | 53.4% | Not comparable |
| SWE-RebenchSource | — | 65.3% | Not comparable |
| React Native EvalsSource | — | 84.1% | Not comparable |
| FrontierCode 1.1 MainSource | — | 26.9% | Not comparable |
Reasoning2 benchmarks
Knowledge16 benchmarks
| Benchmark | Claude Opus 4.5 Thinking | Claude Opus 4.6 | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 40.8% | 37.8% | Claude Opus 4.5 Thinking leads |
| AA-GPQA DiamondSource | 86.6% | 84.0% | Claude Opus 4.5 Thinking leads |
| AA-HLESource | 28.4% | 18.6% | Claude Opus 4.5 Thinking leads |
| AA-Omniscience IndexSource | 13.3% | 3.5% | Claude Opus 4.5 Thinking leads |
| AA-Omniscience AccuracySource | 45.7% | 45.2% | Claude Opus 4.5 Thinking leads |
| AA-Omniscience Hallucination RateSource | 59.8% | 76.0% | Claude Opus 4.5 Thinking leads |
| AA MMLU-ProSource | 89.5% | — | Not comparable |
| GPQASource | — | 91.3% | Not comparable |
| GPQA-DSource | — | 89.2% | Not comparable |
| SuperGPQASource | — | 95% | Not comparable |
| MMLU-ProSource | — | 82% | Not comparable |
| MMLU-Pro (Arcee)Source | — | 89.1% | Not comparable |
| HLESource | — | 53% | Not comparable |
| HLE w/o toolsSource | — | 40% | Not comparable |
| HealthBench HardSource | — | 14.8% | Not comparable |
| MedXpertQA (Text)Source | — | 52.1% | Not comparable |
Math3 benchmarks
Multilingual1 benchmarks
| Benchmark | Claude Opus 4.5 Thinking | Claude Opus 4.6 | Result |
|---|---|---|---|
| AA Global-MMLU-LiteSource | 91.3% | — | Not comparable |
Multimodal6 benchmarks
| Benchmark | Claude Opus 4.5 Thinking | Claude Opus 4.6 | Result |
|---|---|---|---|
| AA-MMMU-ProSource | 74.0% | 72.5% | Claude Opus 4.5 Thinking leads |
| Design Arena WebsiteSource | 1277 | 1325 | Claude Opus 4.6 leads |
| MMMU-ProSource | — | 77.3% | Not comparable |
| ERQASource | — | 51.6% | Not comparable |
| ScreenSpot ProSource | — | 83.1% | Not comparable |
| MedXpertQA (MM)Source | — | 64.8% | Not comparable |
Inst. Following1 benchmarks
| Benchmark | Claude Opus 4.5 Thinking | Claude Opus 4.6 | Result |
|---|---|---|---|
| AA-IFBenchSource | 58.0% | 44.6% | Claude Opus 4.5 Thinking leads |
Frequently Asked Questions (3)
Can I compare Claude Opus 4.5 Thinking and Claude Opus 4.6 on BenchLM yet?
Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.
Why does this comparison show “coming soon”?
BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.
What data is available for Claude Opus 4.5 Thinking and Claude Opus 4.6 today?
Claude Opus 4.6: $5.00 input / $25.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.
Related Comparisons
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.