On 2 November 2026, SemiAnalysis released GDPx v1.0, a benchmark of 206 agentic tasks across 11 domains, and the best model, Claude Opus 5.5, scored 12.0% (GDPx leaderboard). Our verdict: Opus 5.5 is the better general-purpose pick, while Gemini 4 Carbon (10.9% overall at $16.29 per task, against $51.41 for Opus 5.5, per the official leaderboard) is the stronger and cheaper choice for biology workloads, with a caveat about why it wins there.
The headline is not that one model beats another. It is that the strongest agents on the market still fail close to nine in ten professional-grade tasks when the work is hard, private and graded without sympathy.
Last verified: 3 November 2026. Figures come from the GDPx site, which showed data updated on 1 to 2 November.
TL;DR
- GDPx v1.0 covers 206 tasks, 11 domains and 14 specialised environment partners; 20 models were tested (source).
- Claude Opus 5.5 leads at 12.0% and $51.41 per task; Gemini 4 Carbon is second at 10.9% and $16.29; GPT-6 Astra is third at 9.6% and $53.99 (leaderboard).
- Every model scored zero on finance and legal tasks under binary grading.
- Gemini 4 Carbon is the best biology model at 25.6%, but SemiAnalysis suggests weaker safety classifiers help explain this. That is its reading, not a Google statement.
- Pick Opus 5.5 for broad agent work, Gemini 4 Carbon for cost-sensitive science work, and test both on your own data first.
What is the GDPx benchmark?
The GDPx benchmark is a set of long-running agent tasks built with 14 partners that each run a specialised reinforcement-learning environment. Each model gets a workspace, an eight-hour limit and three attempts. Scores are pass@1 averaged, with all 11 domains weighted equally and each partner weighted equally within a domain (methodology).
The domains span chip design, cybersecurity, biology, finance, legal, quant trading, recursive self-improvement, hardware design, materials science, alignment and software engineering. SemiAnalysis positions it as a successor to OpenAI's GDPval, which used 1,320 tasks across 44 occupations (TechTimes). Its argument is that occupational-taxonomy benchmarks aim at the wrong target, because early AI revenue will concentrate where frontier intelligence pays back fastest.
How do the top models compare on GDPx?
On the published leaderboard, the spread between first and third is small and the cost spread is large (leaderboard):
| Model | Score | Cost per task |
|---|---|---|
| Claude Opus 5.5 (Anthropic) | 12.0% | $51.41 |
| Gemini 4 Carbon (Google) | 10.9% | $16.29 |
| GPT-6 Astra (OpenAI) | 9.6% | $53.99 |
| Claude Fable 5.1 | 8.5% | $67.16 |
| Muse Wonder Full (Meta) | 9.0% | not public |
| GPT-6.1 Sol | 8.4% | $9.80 |
| DeepSeek 4.1 Flash 1017 (open weights) | 5.4% | $0.94 |
Gemini 4 Carbon delivers about 91% of the leader's score at roughly a third of the price, a figure derived from the two published numbers above. Claude Opus 5.5 ran in Claude Code, GPT-6 Astra in Codex and Gemini 4 Carbon in Antigravity, each in its native harness, which is worth remembering before comparing scores to your own setup. For other head-to-head views, see our GPT-6 Astra vs Claude Fable 5.1 verdict and the OS 2.0 agent benchmark.
Why did every model score zero on finance and legal?
Under binary grading, a task passes only when every required check passes, and no model managed that in finance or legal (SemiAnalysis). In the finance task "Bellwood-QoE", the best single run passed 8 of 11 required checks across 25 attempts. In the public legal task, a Series B redline, none of the 20 rollouts passed on a binary basis (partial credit averaged 18% (GDPx)).
The practical reading: a single missed clause or reconciliation still fails the work, so a reviewer remains necessary.
Is Gemini 4 Carbon really the best biology model?
On the published numbers, yes: Gemini 4 Carbon scores 25.6% in biology, the highest of any model tested (GDPx). The caveat matters. SemiAnalysis found that Opus 5.5 and GPT-6 Astra appeared to sandbag on cyber, biology and alignment tasks, and attributes Gemini's lead to weaker safety classifiers, stating this is its own interpretation, not a Google statement.
Its secondary leaderboard, which excludes cyber, biology and alignment, changes the order: GPT-6 Astra reaches 11.8%, Opus 5.5 11.7% and Gemini 4 Carbon drops to 9.2% (GDPx, data updated 2 November; corroborated by roboticaguide.com). So the biology lead is partly a question of how willing a model is to run the experiment, not only how well it reasons.
What kind of biology work does the benchmark test?
LatchBio built the 13 biology tasks, 12 private and one public, covering single-cell and spatial transcriptomics, genomics and metagenomics, drug discovery, toxicology and biosecurity. The data is real: tumour biopsies, donor pancreatic islets and public cell atlases modified to prevent memorisation, with each task written by a scientist, checked by two others and graded deterministically (BioBench).
LatchBio documented three recurring failure modes:
- Wrong statistics, such as treating samples from the same subject as independent replicates.
- Mistaking instrument artefacts, for example plate-reader effects, for biological signal.
- Trusting the input instead of judgement, such as analysing every cell type when only some are relevant.
In the public antibody task, models could not reconcile a chip-based binding assay with a cell potency assay, and Opus 5.5 hit that failure mode every time. If you deploy agents in a lab, build these checks into review. Our pieces on multi-agent science workbenches and agentic AI in health care cover the surrounding tooling.
Which model should you choose after GDPx?
Choose Claude Opus 5.5 if you need one model across varied professional tasks. It leads overall and was the best all-around performer, scoring 27.4% in quant trading and 18.7% in hardware design (per-field scores via GDPx; corroborated by roboticaguide.com). Choose Gemini 4 Carbon if the work is biology or software engineering (11.1%, per the GDPx field scores; corroborated by roboticaguide.com) and cost matters, and accept that part of its edge may reflect looser guardrails. Choose GPT-6 Astra for recursive self-improvement (24.9%) and materials science (21.6%), per the GDPx domain table (corroborated by roboticaguide.com). For pure coding, see our real SWE benchmark comparison.
Limits to keep in mind: most tasks are private, so results cannot be independently reproduced, and equal domain weighting means a niche domain moves the average as much as a large one.
FAQ
Q: What is the GDPx benchmark?
A: GDPx is a SemiAnalysis benchmark of 206 agentic tasks across 11 domains, built with 14 environment partners and released on 2 November 2026.
Q: Which model scored highest on GDPx?
A: Claude Opus 5.5 from Anthropic, at 12.0% and $51.41 per task, followed by Gemini 4 Carbon at 10.9% and GPT-6 Astra at 9.6% (leaderboard).
Q: Why is a 12% top score meaningful?
A: Tasks are long, private and graded on deterministic checks, so a pass means the work was fully correct. It shows that unsupervised expert-level work is still out of reach for current agents.
Q: Why did Gemini 4 Carbon win in biology?
A: It scored 25.6% (GDPx), and SemiAnalysis suggests weaker safety classifiers contributed, while noting this is its own reading and not a statement from Google.
Q: Is GDPx a replacement for GDPval?
A: SemiAnalysis pitches it as the successor, arguing that occupation-based benchmarks miss where early AI revenue will concentrate. Whether the community adopts it is not yet known.
This article was produced with AI assistance and checked against the primary sources linked above. Corrections will be logged here if figures change.
Top comments (0)