sonnet-5
Strongest in Computer Use (#31 of 186) and Mathematical Reasoning (#35 of 186); weakest in Knowledge Work (#50 of 186). All seven dimensions are measured.
IQ profile
IQ dimensions
Ranks are among models scored in each dimension. Ranges are model-based estimates, not calibrated confidence intervals.
Benchmark results
28 of 39 Composite IQ benchmarks have a published result for sonnet-5. Benchmarks without a result stay listed so gaps are visible.
Abstract Reasoning IQ 105 · measuredBest: #19 of 55 on Mystery Game Puzzles2/5
Full source leaderboard reconciliation vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 23
Epoch AI vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 14
Mathematical Reasoning IQ 131 · measuredBest: #17 of 49 on ProofBench 1.13/5
Full source leaderboard reconciliation v1.1 · Oct 27
Full source leaderboard reconciliation · Oct 23
Full source leaderboard reconciliation · Oct 23
Academic Reasoning IQ 129 · measuredBest: #38 of 167 on SciCode5/6
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
Programmatic Reasoning IQ 130 · measuredBest: #7 of 25 on SWE-rebench5/6
Full source leaderboard reconciliation · Oct 23
Artificial Analysis v4.3.2 · Oct 27
Full source leaderboard reconciliation · Oct 23
Full source leaderboard reconciliation v2 · Oct 27
Computer Use IQ 126 · measuredBest: #11 of 45 on BrowseComp3/5
Full source leaderboard reconciliation · Oct 23
Full source leaderboard reconciliation · Oct 23
Arena.ai Agent Arena · Nov 19
Reliability IQ 123 · measuredBest: #9 of 96 on BullshitBench v24/6
Full source leaderboard reconciliation · Oct 23
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
Full source leaderboard reconciliation · Oct 23
Knowledge Work IQ 123 · measuredBest: #31 of 124 on GDPval-AA v2.1 normalized score6/6
Artificial Analysis v4.3.2 · Oct 20
Artificial Analysis v4.3.2 · Oct 27
Full source leaderboard reconciliation vpass^5-2026-09-29 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
Full source leaderboard reconciliation v1117-task-strict-2026-09-29 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
Release & availability
Release details on record for this model.
- Released
- Developer
- Anthropic
- Weights
- ProprietaryHosted access only
- Context
- 1,000,000 tokens
- API price
- $2 in · $10 outper 1M tokens · full pricing
About this score
How much of sonnet-5's IQ is measured, and how the rest is estimated.
Every score in the benchmark tables comes from its source unchanged. Composite IQ averages all seven dimensions equally.
Every dimension has at least one published result. Missing benchmarks can also draw on its predecessor, Sonnet 4.6; a predecessor is an estimation input, not evidence that this model has the predecessor's measured results.
Benchmark versions and evaluation harnesses can differ between sources, so small gaps between models may not be meaningful.
Compare sonnet-5
Side-by-side pages for the models it is most often weighed against.
Frequently asked questions
Quick answers about sonnet-5, drawn from the same data as the rest of this page.
How AI IQ scores models →Get this data from the API →- What is the IQ of sonnet-5?
- sonnet-5 has an estimated IQ of 124, which ranks #37 out of 186 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.
- What is sonnet-5 best at?
- Among the dimensions with published benchmark results, sonnet-5 ranks highest in Computer Use (IQ 126, #31 of 186) and Mathematical Reasoning (IQ 131, #35 of 186). Its lowest-ranked measured dimension is Knowledge Work (IQ 123, #50 of 186).
- What is the EQ of sonnet-5?
- sonnet-5 has an estimated EQ of 117. EQ measures emotional reasoning — how well a model reads and responds to emotional context — and is scored separately from IQ.
- Which benchmarks has sonnet-5 been tested on?
- sonnet-5 has published results on 28 of the 39 benchmarks behind AI IQ's Composite IQ, including BullshitBench v2, AA Omniscience, AA Long Context Reasoning v1.1, SciCode and BrowseComp.
- How much does sonnet-5 cost?
- sonnet-5 costs $2.00 per million input tokens and $10.00 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $38.70 per million input-plus-output tokens.
- Is sonnet-5 open source?
- No — sonnet-5 is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
- Who developed sonnet-5?
- sonnet-5 was developed by Anthropic, based in the United States.
- When was sonnet-5 released?
- sonnet-5 was publicly released on June 30, 2026.
- How large is the context window of sonnet-5?
- sonnet-5 supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.
- How fast is sonnet-5?
- In independent measurements, sonnet-5 generates about 83 tokens per second, with a typical response time of about 205 seconds.