AnthropicReleased Jun 30, 2026
Proprietary

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.

Composite IQ ?
124
#37 of 186 ranked models · ahead of 81%
Anthropic's #8 model, behind fable-5.2 (144)
Effective cost
$38.70/1M
$2 in · $10 out
Speed
83tok/s
205s typical response
Context
1Mtokens
1,000,000 tokens in
Evidence
7of 7 dims
28 of 39 benchmarks

IQ profile

Seven dimensions, averaged equally into Composite IQ
Compare shape with
100 avg human130160● Abstract105#52● Math131#35● Academic129#53● Coding130#49● Computer Use126#31● Reliability123#39● Knowledge Work123#50
Measured95% range
#1 in dimensionTop-10 median

IQ dimensions

Ranks are among models scored in each dimension. Ranges are model-based estimates, not calibrated confidence intervals.

DimensionIQPosition · 70–160RankEvidencevs Top 10
105measured
#52 / 226
2/5
-27.5
131measured
#35 / 186
3/5
-18.5
129measured
#53 / 228
5/6
-6
130measured
#49 / 187
5/6
-21
126measured
#31 / 186
3/5
-20.5
123measured
#39 / 188
4/6
-12.5
123measured
#50 / 186
6/6
-9
sonnet-595% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

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
BenchmarkScorePercentileRankLeader · source
Mystery Game Puzzles
Full source leaderboard reconciliation vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 23
35.0%
#19 / 55
Leader gpt-6-astra · 84.0%
Full source leaderboard reconciliation vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 23
Chess Puzzles
Epoch AI vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 14
35.0%
#27 / 76
Leader gpt-6-astra · 72.0%
Epoch AI vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 14
Not yet reported
ARC-AGI-3ARC-AGI-2ARC-AGI-1
Mathematical Reasoning IQ 131 · measuredBest: #17 of 49 on ProofBench 1.13/5
BenchmarkScorePercentileRankLeader · source
ProofBench 1.1
Full source leaderboard reconciliation v1.1 · Oct 27
77.0%
#17 / 49
Leader fable-5.1 · 100%
Full source leaderboard reconciliation v1.1 · Oct 27
FrontierMath Tier 1-3
Full source leaderboard reconciliation · Oct 23
65.6%
#39 / 90
Leader fable-5.2 · 95.1%
Full source leaderboard reconciliation · Oct 23
FrontierMath Tier 4
Full source leaderboard reconciliation · Oct 23
29.3%
#38 / 78
Leader fable-5.2 · 100%
Full source leaderboard reconciliation · Oct 23
Not yet reported
MathArenaAIME
Academic Reasoning IQ 129 · measuredBest: #38 of 167 on SciCode5/6
BenchmarkScorePercentileRankLeader · source
SciCode
Artificial Analysis v4.3.2 · Oct 27
54.3%
#38 / 167
Leader opus-5.5 · 66.9%
Artificial Analysis v4.3.2 · Oct 27
Humanity's Last Exam
Artificial Analysis v4.3.2 · Oct 27
41.3%
#42 / 167
Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 27
CritPt
Artificial Analysis v4.3.2 · Oct 27
16.9%
#40 / 159
Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 27
GPQA Diamond
Artificial Analysis v4.3.2 · Oct 27
91.1%
#38 / 147
Leader gpt-6-astra · 96.1%
Artificial Analysis v4.3.2 · Oct 27
MMMU-Pro
Artificial Analysis v4.3.2 · Oct 27
77.3%
#43 / 90
Leader fable-5.1 · 90.6%
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
MMLU-Pro
Programmatic Reasoning IQ 130 · measuredBest: #7 of 25 on SWE-rebench5/6
BenchmarkScorePercentileRankLeader · source
SWE-rebench
Full source leaderboard reconciliation · Oct 23
56.8%
#7 / 25
Leader fable-5 · 64.5%
Full source leaderboard reconciliation · Oct 23
Terminal-Bench 4.0
Artificial Analysis v4.3.2 · Oct 27
14.1%
#39 / 109
Leader Kimi K3.1 Pro · 67.2%
Artificial Analysis v4.3.2 · Oct 27
ProgramBench
Full source leaderboard reconciliation · Oct 23
13.5%
#25 / 63
Leader opus-5.5 · 65.0%
Full source leaderboard reconciliation · Oct 23
LiveCodeBench
Vals.ai · Aug 4
82.4%
#28 / 61
Leader Fugu Ultra v1.0 · 93.2%
Vals.ai · Aug 4
IOI V2
Full source leaderboard reconciliation v2 · Oct 27
45.0%
#32 / 43
Leader Gemini 4 Argon · 100%
Full source leaderboard reconciliation v2 · Oct 27
Not yet reported
MirrorCode
Computer Use IQ 126 · measuredBest: #11 of 45 on BrowseComp3/5
BenchmarkScorePercentileRankLeader · source
BrowseComp
Full source leaderboard reconciliation · Oct 23
84.7%
#11 / 45
Leader Kimi K3.1 Pro · 92.1%
Full source leaderboard reconciliation · Oct 23
OSWorld-Verified
Full source leaderboard reconciliation · Oct 23
81.2%
#6 / 24
Leader fable-5 · 85.0%
Full source leaderboard reconciliation · Oct 23
Arena.ai Agent Arena
Arena.ai Agent Arena · Nov 19
1.0
#34 / 77
Leader fable-5.2 · 27.4
Arena.ai Agent Arena · Nov 19
Not yet reported
MCP AtlasAgents' Last Exam
Reliability IQ 123 · measuredBest: #9 of 96 on BullshitBench v24/6
BenchmarkScorePercentileRankLeader · source
BullshitBench v2
Full source leaderboard reconciliation · Oct 23
78.0%
#9 / 96
Leader opus-4.8 · 94.0%
Full source leaderboard reconciliation · Oct 23
AA Omniscience
Artificial Analysis v4.3.2 · Oct 27
16.5
#32 / 158
Leader opus-5.5 · 46.4
Artificial Analysis v4.3.2 · Oct 27
AA Long Context Reasoning v1.1
Artificial Analysis v4.3.2 · Oct 27
82.0%
#32 / 154
Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 27
SimpleQA Verified
Full source leaderboard reconciliation · Oct 23
33.7%
#66 / 86
Leader fable-5.2 · 94.0%
Full source leaderboard reconciliation · Oct 23
Not yet reported
IFBenchFACTS Grounding
Knowledge Work IQ 123 · measuredBest: #31 of 124 on GDPval-AA v2.1 normalized score6/6
BenchmarkScorePercentileRankLeader · source
GDPval-AA v2.1 normalized score
Artificial Analysis v4.3.2 · Oct 20
48.2%
#31 / 124
Leader opus-5.5 · 68.3%
Artificial Analysis v4.3.2 · Oct 20
AA-Briefcase v1.1 Elo
Artificial Analysis v4.3.2 · Oct 27
1,357
#39 / 116
Leader sonnet-5.5 · 1,816
Artificial Analysis v4.3.2 · Oct 27
AA-AnalystAgent
Full source leaderboard reconciliation vpass^5-2026-09-29 · Oct 27
46.3%
#15 / 35
Leader gemini-3.7-flash · 60.0%
Full source leaderboard reconciliation vpass^5-2026-09-29 · Oct 27
GDP.pdf
Artificial Analysis v4.3.2 · Oct 27
13.2%
#49 / 111
Leader Muse Wonder Full · 32.6%
Artificial Analysis v4.3.2 · Oct 27
EnterpriseOps-Gym-AA
Full source leaderboard reconciliation v1117-task-strict-2026-09-29 · Oct 27
44.7%
#14 / 31
Leader fable-5 · 51.1%
Full source leaderboard reconciliation v1117-task-strict-2026-09-29 · Oct 27
AutomationBench-AA
Artificial Analysis v4.3.2 · Oct 27
36.5%
#52 / 112
Leader Gemini 4 Carbon · 77.8%
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.

28/ 39benchmark results
7/ 7dimensions measured
0estimated
2/5Abstract
3/5Math
5/6Academic
5/6Coding
3/5Computer Use
4/6Reliability
6/6Knowledge Work
Bar height = share of benchmarks with resultsEstimatedNo score
Measured results are shown as published

Every score in the benchmark tables comes from its source unchanged. Composite IQ averages all seven dimensions equally.

How gaps are handled

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.

A missing result is not a zero

Benchmark versions and evaluation harnesses can differ between sources, so small gaps between models may not be meaningful.

Read the scoring methodology →

Compare sonnet-5

Side-by-side pages for the models it is most often weighed against.

sonnet-5Comparison model
Browse all comparisons →

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.