The arms race to construct smarter AI fashions has a measurement downside: the assessments used to rank them have gotten out of date virtually as shortly because the fashions enhance. On Monday, Synthetic Evaluation, an unbiased AI benchmarking group whose rankings are carefully watched by builders and enterprise patrons, launched a significant overhaul to its Intelligence Index that essentially adjustments how the business measures AI progress.
The brand new Intelligence Index v4.0 incorporates 10 evaluations spanning brokers, coding, scientific reasoning, and common data. However the adjustments go far deeper than shuffling check names. The group eliminated three staple benchmarks — MMLU-Professional, AIME 2025, and LiveCodeBench — which have lengthy been cited by AI firms of their advertising supplies. Of their place, the brand new index introduces evaluations designed to measure whether or not AI methods can full the form of work that folks really receives a commission to do.
sort: embedded-entry-inline id: 1bCmRrroGCdUb07IuaHysL
"This index shift displays a broader transition: intelligence is being measured much less by recall and extra by economically helpful motion," noticed Aravind Sundar, a researcher who responded to the announcement on X (previously Twitter).
Why AI benchmarks are breaking: The issue with assessments that high fashions have already mastered
The benchmark overhaul addresses a rising disaster in AI analysis: the main fashions have change into so succesful that conventional assessments can now not meaningfully differentiate between them. The brand new index intentionally makes the curve more durable to climb. In response to Synthetic Evaluation, high fashions now rating 50 or beneath on the brand new v4.0 scale, in comparison with 73 on the earlier model — a recalibration designed to revive headroom for future enchancment.
This saturation downside has plagued the business for months. When each frontier mannequin scores within the ninetieth percentile on a given check, the check loses its usefulness as a decision-making software for enterprises attempting to decide on which AI system to deploy. The brand new methodology makes an attempt to resolve this by weighting 4 classes equally — Brokers, Coding, Scientific Reasoning, and Genera l— whereas introducing evaluations the place even probably the most superior methods nonetheless battle.
The outcomes beneath the brand new framework present OpenAI's GPT-5.2 with prolonged reasoning effort claiming the highest spot, adopted carefully by Anthropic's Claude Opus 4.5 and Google's Gemini 3 Professional. OpenAI describes GPT-5.2 as "probably the most succesful mannequin collection but for skilled data work," whereas Anthropic's Claude Opus 4.5 scores greater than GPT-5.2 on SWE-Bench Verified, a check set evaluating software program coding talents.
GDPval-AA: The brand new benchmark testing whether or not AI can do your job
Probably the most vital addition to the brand new index is GDPval-AA, an analysis based mostly on OpenAI's GDPval dataset that assessments AI fashions on real-world economically precious duties throughout 44 occupations and 9 main industries. In contrast to conventional benchmarks that ask fashions to resolve summary math issues or reply multiple-choice trivia, GDPval-AA measures whether or not AI can produce the deliverables that professionals really create: paperwork, slides, diagrams, spreadsheets, and multimedia content material.
Fashions obtain shell entry and net searching capabilities by what Synthetic Evaluation calls "Stirrup," its reference agentic harness. Scores are derived from blind pairwise comparisons, with ELO scores frozen on the time of analysis to make sure index stability.
Underneath this framework, OpenAI's GPT-5.2 with prolonged reasoning leads with an ELO rating of 1442, whereas Anthropic's Claude Opus 4.5 non-thinking variant follows at 1403. Claude Sonnet 4.5 trails at 1259.
On the unique GDPval analysis, GPT-5.2 beat or tied high business professionals on 70.9% of well-specified duties, based on OpenAI. The corporate claims GPT-5.2 "outperforms business professionals at well-specified data work duties spanning 44 occupations," with firms together with Notion, Field, Shopify, Harvey, and Zoom observing "state-of-the-art long-horizon reasoning and tool-calling efficiency."
The emphasis on economically measurable output is a philosophical shift in how the business thinks about AI functionality. Fairly than asking whether or not a mannequin can cross a bar examination or remedy competitors math issues — achievements that generate headlines however don't essentially translate to office productiveness — the brand new benchmarks ask whether or not AI can really do jobs.
Graduate-level physics issues expose the boundaries of immediately's most superior AI fashions
Whereas GDPval-AA measures sensible productiveness, one other new analysis referred to as CritPT reveals simply how far AI methods stay from true scientific reasoning. The benchmark assessments language fashions on unpublished, research-level reasoning duties throughout trendy physics, together with condensed matter, quantum physics, and astrophysics.
CritPT was developed by greater than 50 energetic physics researchers from over 30 main establishments. Its 71 composite analysis challenges simulate full-scale analysis tasks on the entry stage — similar to the warm-up workout routines a hands-on principal investigator would possibly assign to junior graduate college students. Each downside is hand-curated to supply a guess-resistant, machine-verifiable reply.
The outcomes are sobering. Present state-of-the-art fashions stay removed from reliably fixing full research-scale challenges. GPT-5.2 with prolonged reasoning leads the CritPT leaderboard with a rating of simply 11.5%, adopted by Google's Gemini 3 Professional Preview and Anthropic's Claude 4.5 Opus Considering variant. These scores recommend that regardless of outstanding progress on consumer-facing duties, AI methods nonetheless battle with the form of deep reasoning required for scientific discovery.
AI hallucination charges: Why probably the most correct fashions aren't at all times probably the most reliable
Maybe probably the most revealing new analysis is AA-Omniscience, which measures factual recall and hallucination throughout 6,000 questions masking 42 economically related subjects inside six domains: Enterprise, Well being, Legislation, Software program Engineering, Humanities & Social Sciences, and Science/Engineering/Arithmetic.
The analysis produces an Omniscience Index that rewards exact data whereas penalizing hallucinated responses — offering perception into whether or not a mannequin can distinguish what it is aware of from what it doesn't. The findings expose an uncomfortable reality: excessive accuracy doesn’t assure low hallucination. Fashions with the best accuracy usually fail to steer on the Omniscience Index as a result of they have a tendency to guess somewhat than abstain when unsure.
Google's Gemini 3 Professional Preview leads the Omniscience Index with a rating of 13, adopted by Claude Opus 4.5 Considering and Gemini 3 Flash Reasoning, each at 10. Nonetheless, the breakdown between accuracy and hallucination charges reveals a extra complicated image.
On uncooked accuracy, Google's two fashions lead with scores of 54% and 51% respectively, adopted by Claude 4.5 Opus Considering at 43%. However Google's fashions additionally show greater hallucination charges than peer fashions, scoring 88% and 85%. Anthropic's Claude 4.5 Sonnet Considering and Claude Opus 4.5 Considering present hallucination charges of 48% and 58% respectively, whereas GPT-5.1 with excessive reasoning effort achieves 51%—the second-lowest hallucination fee examined.
Each Omniscience Accuracy and Hallucination Price contribute 6.25% weighting every to the general Intelligence Index v4.
Contained in the AI arms race: How OpenAI, Google, and Anthropic stack up beneath new testing
The benchmark reshuffling arrives at an particularly turbulent second within the AI business. All three main frontier mannequin builders have launched main new fashions inside only a few weeks — and Gemini 3 nonetheless holds the highest spot on a lot of the leaderboards on LMArena, a broadly cited benchmarking software used to check LLMs.
Google's November launch of Gemini 3 prompted OpenAI to declare a "code pink" effort to enhance ChatGPT. OpenAI is relying on its GPT household of fashions to justify its $500 billion valuation and over $1.4 trillion in deliberate spending. "We introduced this code pink to actually sign to the corporate that we need to marshal assets in a single specific space," stated Fidji Simo, CEO of functions at OpenAI. Altman advised CNBC he anticipated OpenAI to exit its code pink by January.
Anthropic responded with Claude Opus 4.5 on November 24, reaching an SWE-Bench Verified accuracy rating of 80.9% — reclaiming the coding crown from each GPT-5.1-Codex-Max and Gemini 3. The launch marked Anthropic's third main mannequin launch in two months. Microsoft and Nvidia have since introduced multi-billion-dollar investments in Anthropic, boosting its valuation to about $350 billion.
How Synthetic Evaluation assessments AI fashions: A have a look at the unbiased benchmarking course of
Synthetic Evaluation emphasizes that every one evaluations are run independently utilizing a standardized methodology. The group states that its "methodology emphasizes equity and real-world applicability," estimating a 95% confidence interval for the Intelligence Index of lower than ±1% based mostly on experiments with greater than 10 repeats on sure fashions.
The group's revealed methodology defines key phrases that enterprise patrons ought to perceive. In response to the methodology documentation, Synthetic Evaluation considers an "endpoint" to be a hosted occasion of a mannequin accessible through an API — which means a single mannequin might have a number of endpoints throughout totally different suppliers. A "supplier" is an organization that hosts and supplies entry to a number of mannequin endpoints or methods. Critically, Synthetic Evaluation distinguishes between "open weights" fashions, whose weights have been launched publicly, and really open-source fashions—noting that many open LLMs have been launched with licenses that don’t meet the complete definition of open-source software program.
The methodology additionally clarifies how the group standardizes token measurement: it makes use of OpenAI tokens as measured with OpenAI's tiktoken bundle as a regular unit throughout all suppliers to allow truthful comparisons.
What the brand new AI Intelligence Index means for enterprise know-how selections in 2026
For technical decision-makers evaluating AI methods, the Intelligence Index v4.0 supplies a extra nuanced image of functionality than earlier benchmark compilations. The equal weighting throughout brokers, coding, scientific reasoning, and common data implies that enterprises with particular use circumstances might need to study category-specific scores somewhat than relying solely on the mixture index.
The introduction of hallucination measurement as a definite, weighted issue addresses some of the persistent issues in enterprise AI adoption. A mannequin that seems extremely correct however often hallucinates when unsure poses vital dangers in regulated industries like healthcare, finance, and regulation.
The Synthetic Evaluation Intelligence Index is described as "a text-only, English language analysis suite." The group benchmarks fashions for picture inputs, speech inputs, and multilingual efficiency individually.
The response to the announcement has been largely optimistic. "It’s nice to see the index evolving to scale back saturation and focus extra on agentic efficiency," wrote one commenter in an X.com publish. "Together with real-world duties like GDPval-AA makes the scores way more related for sensible use."
Others struck a extra formidable notice. "The brand new wave of fashions that’s nearly to return will go away all of them behind," predicted one observer. "By the top of the yr the singularity might be plain."
However whether or not that prediction proves prophetic or untimely, one factor is already clear: the period of judging AI by how effectively it solutions check questions is ending. The brand new commonplace is easier and much more consequential — can it do the work?
