APEX Benchmarks
The AI Productivity Index family of benchmarks assesses whether frontier AI models can perform economically valuable tasks across professional services, medicine, and software engineering.
Our benchmarks
Each benchmark tests a different dimension of professional capability. All tasks are built with Mercor experts and leading industry partners.
APEX-Agents
Long-horizon, cross-application tasks in professional services
Tests whether AI agents can complete multi-hour professional tasks across investment banking, corporate law, and management consulting, using real tools in Google Suite.
Opus 5.5Max
73.5% ±4.9%
Fable 5.1Max
68.6% ±4.9%
Gemini 3.7 FlashHigh
67.8% ±5.1%
Opus 5Max
65.8% ±5.1%
Grok 4.6xHigh
65.3% ±5.2%
APEX-Accounting
Long-horizon, cross-application tasks in professional accounting
Measuring AI agents ability to complete professional accounting tasks across tools like accounting software, spreadsheets, and PDFs.
Opus 5.5Max
61.8% ±4.0%
Fable 5.1Max
61.0% ±3.7%
GPT-6 AstraMax
57.9% ±3.8%
Fable 5Max
56.4% ±3.6%
Opus 5Max
54.5% ±3.9%
APEX-SWE
Real-world software engineering across integration and observability
Measures AI performance on real-world software engineering tasks, from bug fixes to feature builds. Built in collaboration with Cognition.
Opus 5.5Max
67.6% ±5.9%
Opus 5Max
63.7% ±6.4%
Fable 5.1Max
63.6% ±6.3%
Fable 5Max
58.8% ±6.4%
Grok 4.6High
56.4% ±6.2%
APEX-1
Single-turn text tasks
Tests whether frontier models can perform economically valuable tasks across professional domains including investment banking, corporate law, management consulting, and medicine.
Muse Spark 1.2xHigh
75.6% ±2.3%
Muse Spark 1.3xHigh
74.0% ±2.3%
Fable 5.1Max
73.8% ±2.7%
Muse Spark 1.1xHigh
73.8% ±2.2%
GPT-5.6 SolMax • Pro
73.1% ±2.4%
Mercor-extended benchmarks
Open-source benchmarks extended with new expert-built Mercor tasks.
BrowseComp Extended
130 questions requiring agents to persistently navigate the internet to locate hard-to-find, entangled information. Tests information-discovery competence through persistence and creative problem-solving.
GPT-6 SolMax
Score on the original open-source benchmark: 89.4% / Score on this Mercor-extended benchmark: 63.2%
Opus 5.5Max
Score on the original open-source benchmark: 88.5% / Score on this Mercor-extended benchmark: 60.5%
DeepSeek-V4.1-FlashMax
Score on the original open-source benchmark: 85.8% / Score on this Mercor-extended benchmark: 48.2%
GPT-6 LunaMax
Score on the original open-source benchmark: 83.3% / Score on this Mercor-extended benchmark: 47.2%
Fable 5High
Score on the original open-source benchmark: 82.5% / Score on this Mercor-extended benchmark: 44.5%
CharXiv Extended
Evaluates multimodal models on realistic chart understanding using 2,323 hand-curated arXiv charts, with descriptive questions (basic elements) and reasoning questions (synthesis across complex elements).
Muse Spark 1.1xHigh
Score on the original open-source benchmark: 95.2% / Score on this Mercor-extended benchmark: 86.4%
GPT-6 AstraxHigh
Score on the original open-source benchmark: 95.8% / Score on this Mercor-extended benchmark: 85.1%
Opus 5.5Max
Score on the original open-source benchmark: 96.4% / Score on this Mercor-extended benchmark: 84.7%
GPT-6 SolMax
Score on the original open-source benchmark: 95.0% / Score on this Mercor-extended benchmark: 83.8%
Qwen3.8-MaxxHigh
Score on the original open-source benchmark: 94.1% / Score on this Mercor-extended benchmark: 82.9%
GDPval Extended
Evaluates models on real-world, economically valuable tasks spanning most BLS work activities for 44 occupations across nine major GDP sectors.
Opus 5.5Max
Score on the original open-source benchmark: 88.3% / Score on this Mercor-extended benchmark: 75.8%
Fable 5.1Max
Score on this Mercor-extended benchmark: 68.7%
Fable 5Max
Score on the original open-source benchmark: 78.6% / Score on this Mercor-extended benchmark: 65.3%
GPT-6 AstraMax
Score on this Mercor-extended benchmark: 64.1%
Opus 5Max
Score on the original open-source benchmark: 85.6% / Score on this Mercor-extended benchmark: 62.9%
HLE Extended
Tests models on 2,158 frontier-level, closed-ended academic questions requiring genuine subject mastery rather than retrieval.
GPT-5.6 SolMax • Pro
Score on this Mercor-extended benchmark: 77.3%
GPT-5.6 TerraMax
Score on the original open-source benchmark: 44.9% / Score on this Mercor-extended benchmark: 70.7%
Opus 5High
Score on the original open-source benchmark: 52.0% / Score on this Mercor-extended benchmark: 61.0%
Fable 5High
Score on the original open-source benchmark: 51.5% / Score on this Mercor-extended benchmark: 58.7%
GPT-5.6 LunaMax
Score on the original open-source benchmark: 39.6% / Score on this Mercor-extended benchmark: 57.5%
Long Context Reasoning (AA-LCR) Extended
Long Context Reasoning (AA-LCR): 100 hard questions over 234 documents in 30 sets (~100k tokens/question) that require synthesizing information across multiple documents and complex reasoning rather than simple retrieval.
GPT-5.6 SolMax • Pro
Score on the original open-source benchmark: 80.0% / Score on this Mercor-extended benchmark: 79.5%
GPT-5.6 TerraMax
Score on the original open-source benchmark: 81.8% / Score on this Mercor-extended benchmark: 74.4%
Opus 5.5Max
Score on the original open-source benchmark: 84.0% / Score on this Mercor-extended benchmark: 74.2%
Opus 5Max
Score on the original open-source benchmark: 80.5% / Score on this Mercor-extended benchmark: 73.9%
Fable 5.1High
Score on the original open-source benchmark: 81.5% / Score on this Mercor-extended benchmark: 73.0%
MedXpertQA MM Extended
200 multimodal multiple-choice medical questions spread across 11 body systems. Each task requires multi-step reasoning over clinical images and patient details.
Opus 5.5Max
Score on the original open-source benchmark: 85.7% / Score on this Mercor-extended benchmark: 71.2%
GPT-6 SolMax
Score on the original open-source benchmark: 81.3% / Score on this Mercor-extended benchmark: 68.0%
Fable 5.1High
Score on the original open-source benchmark: 79.7% / Score on this Mercor-extended benchmark: 66.0%
GPT-5.6 SolMax • Pro
Score on the original open-source benchmark: 79.5% / Score on this Mercor-extended benchmark: 64.7%
Opus 5Max
Score on the original open-source benchmark: 79.8% / Score on this Mercor-extended benchmark: 64.1%
MMMU-Pro Extended
A more robust multimodal benchmark that filters text-only-solvable questions, expands answer options, and adds vision-only inputs (text embedded in images) to test true joint visual+textual reasoning. Forces models to 'see' and 'read' simultaneously.
GPT-6 AstraMax
Score on this Mercor-extended benchmark: 60.0%
GPT-5.6 SolMax • Pro
Score on this Mercor-extended benchmark: 51.9%
GPT-6 SolMax
Score on the original open-source benchmark: 83.0% / Score on this Mercor-extended benchmark: 51.9%
Opus 5.5Max
Score on the original open-source benchmark: 87.4% / Score on this Mercor-extended benchmark: 51.0%
GPT-5.6 TerraMax
Score on the original open-source benchmark: 80.9% / Score on this Mercor-extended benchmark: 47.4%
SWE Atlas - Codebase QnA Extended
Benchmarks coding agents beyond issue resolution across Codebase Q&A (124 tasks), test writing (90), and refactoring (70), combining programmatic validation with rubric-based software-quality scoring (maintainability, abstractions, hygiene). Uses under-specified, agentic task formulations.
Opus 5.5Max
Score on the original open-source benchmark: 48.9% / Score on this Mercor-extended benchmark: 43.3%
Opus 5Max
Score on the original open-source benchmark: 50.3% / Score on this Mercor-extended benchmark: 40.0%
DeepSeek-V4.1-FlashMax
Score on the original open-source benchmark: 53.5% / Score on this Mercor-extended benchmark: 36.7%
Sonnet 5Max
Score on the original open-source benchmark: 39.5% / Score on this Mercor-extended benchmark: 32.7%
GPT-6 SolMax
Score on the original open-source benchmark: 44.1% / Score on this Mercor-extended benchmark: 31.3%
SWE-bench Verified Extended
Tests whether LLMs can resolve real-world GitHub issues by editing codebases, spanning 500 problems from 12 popular Python repos and requiring multi-file, long-context changes.
DeepSeek-V4.1-FlashMax
Score on the original open-source benchmark: 82.9% / Score on this Mercor-extended benchmark: 82.7%
Opus 5Max
Score on the original open-source benchmark: 93.5% / Score on this Mercor-extended benchmark: 82.0%
Fable 5Max
Score on the original open-source benchmark: 95.9% / Score on this Mercor-extended benchmark: 78.7%
GPT-5.6 TerraMax
Score on the original open-source benchmark: 77.8% / Score on this Mercor-extended benchmark: 78.7%
GPT-5.6 LunaMax
Score on the original open-source benchmark: 76.2% / Score on this Mercor-extended benchmark: 74.7%
Terminal-Bench 2.1 Extended
Evaluates AI agents on hard, realistic long-horizon command-line tasks — 89 curated tasks with unique environments, human-written solutions, and verification tests.
Opus 5.5Max
Score on the original open-source benchmark: 83.5% / Score on this Mercor-extended benchmark: 47.5%
GPT-6 SolMax
Score on the original open-source benchmark: 85.4% / Score on this Mercor-extended benchmark: 42.4%
DeepSeek-V4.1-FlashMax
Score on the original open-source benchmark: 86.5% / Score on this Mercor-extended benchmark: 38.4%
GPT-5.5xHigh
Score on the original open-source benchmark: 83.1% / Score on this Mercor-extended benchmark: 38.0%
GPT-5.6 SolxHigh
Score on the original open-source benchmark: 84.6% / Score on this Mercor-extended benchmark: 37.4%
Open-source benchmarks
Popular open-source benchmarks, independently evaluated by Mercor.
SciCode
An expert-built benchmark of 80 real lab problems across 16 scientific fields, scored on its 288 test subproblems. Unlike typical coding benchmarks, it pairs domain science with programming skill.
Opus 5.5Max
57.4%
Fable 5Max
49.0%
GPT-6 AstraxHigh
47.5%
Fable 5.1High
46.3%
GPT-6 LunaMax
46.0%
Terminal-Bench 2.1
Evaluates AI agents on hard, realistic long-horizon command-line tasks — 89 curated tasks with unique environments, human-written solutions, and verification tests.
DeepSeek-V4.1-FlashMax
86.5%
GPT-6 AstraxHigh
85.4%
GPT-6 SolMax
85.4%
GPT-5.6 SolxHigh
84.6%
Grok 4.6xHigh
84.6%
SWE Atlas - Codebase QnA
Benchmarks coding agents beyond issue resolution across Codebase Q&A (124 tasks), test writing (90), and refactoring (70), combining programmatic validation with rubric-based software-quality scoring (maintainability, abstractions, hygiene). Uses under-specified, agentic task formulations.
DeepSeek-V4.1-FlashMax
53.5%
Kimi K3Max
52.7%
Opus 5Max
50.3%
Opus 5.5Max
48.9%
Opus 4.7Max
47.0%
SWE-bench Verified
Tests whether LLMs can resolve real-world GitHub issues by editing codebases, spanning 500 problems from 12 popular Python repos and requiring multi-file, long-context changes.
Opus 5.5Max
98.2%
Fable 5Max
95.9%
Opus 5Max
93.5%
Fable 5.1High
92.1%
Opus 4.8Max
88.5%
Long Context Reasoning (AA-LCR)
Long Context Reasoning (AA-LCR): 100 hard questions over 234 documents in 30 sets (~100k tokens/question) that require synthesizing information across multiple documents and complex reasoning rather than simple retrieval.
Opus 5.5Max
84.0%
GPT-5.5xHigh
82.8%
GPT-5.4xHigh
82.5%
GPT-5.6 TerraMax
81.8%
Fable 5Max
81.5%
MMLU-Pro
An enhanced MMLU adding harder, reasoning-focused questions and expanding choices from 4 to 10 options. The MMLU benchmark evaluates an AI model's general knowledge and reasoning skills using multiple-choice questions across 57 academic and professional subjects.
Opus 5.5Max
93.4%
Opus 5Max
92.0%
Fable 5.1High
91.5%
Gemini 3.1 ProHigh
91.3%
GPT-6 AstraxHigh
91.0%
MMMU-Pro
A more robust multimodal benchmark that filters text-only-solvable questions, expands answer options, and adds vision-only inputs (text embedded in images) to test true joint visual+textual reasoning. Forces models to 'see' and 'read' simultaneously.
Opus 5.5Max
87.4%
GPT-6 AstraxHigh
86.8%
Gemini 3.7 FlashHigh
85.2%
Gemini 3.5 FlashHigh
84.7%
Gemini 3.1 ProHigh
84.3%
AdvancedIF
Evaluates complex, multi-turn, and system-level instruction following via expert-curated rubrics over 1,600+ prompts. Paired with a reinforcement-learning method for improving instruction following.
Gemini 3.1 ProHigh
86.7%
Gemini 3.6 FlashHigh
85.3%
DeepSeek-V4.1-FlashMax
84.0%
Opus 5.5Max
82.8%
Fable 5.1High
82.6%
AIME 2025
Competition-mathematics benchmark drawn from the 2025 American Invitational Mathematics Examination; each answer is an integer 0-999. Measures advanced multi-step mathematical problem-solving and reasoning.
Opus 5Max
100.0%
Fable 5Max
100.0%
DeepSeek-V4-FlashMax
100.0%
GPT-5.5xHigh
100.0%
GPT-5.6 SolMax • Pro
100.0%
BrowseComp
130 questions requiring agents to persistently navigate the internet to locate hard-to-find, entangled information. Tests information-discovery competence through persistence and creative problem-solving.
GPT-6 AstraxHigh
94.2%
GPT-5.6 SolxHigh
90.6%
GPT-6 SolMax
89.4%
Kimi K3Max
89.0%
Opus 5.5Max
88.5%
CharXiv
Evaluates multimodal models on realistic chart understanding using 2,323 hand-curated arXiv charts, with descriptive questions (basic elements) and reasoning questions (synthesis across complex elements).
Opus 5.5Max
96.4%
GPT-6 AstraMax
96.1%
Gemini 3.8 FlashHigh
95.4%
Gemini 3.7 FlashHigh
95.3%
Muse Spark 1.1xHigh
95.2%
CVDP
517 RTL design and verification problems from real hardware workflows — spec-to-RTL, code completion and modification, module reuse, debugging, testbench generation, and RTL/testbench comprehension Q&A.
Opus 5.5Max
63.0%
Fable 5.1Max
61.6%
Opus 5Max
61.1%
Grok 4.6xHigh
57.1%
GPT-5.6 SolMax
54.7%
DeepResearch Bench II
A bilingual benchmark of 130 open-ended research briefs across 22 domains, scored against 9,287 expert-written criteria. Each task is derived from a real review article that the model is explicitly forbidden from consulting, and credit only comes from independently rediscovering the findings.
Opus 5High
56.1%
Sonnet 4.6High
53.3%
Opus 5.5Max
53.3%
DeepSeek-V4.1-FlashMax
53.2%
GPT 5.6 SolMedium
51.5%
DeepSWE v1.1
113 original software engineering tasks spanning 91 repositories and 5 languages. Each task requires large, novel fixes not sourced from existing public commits.
Opus 5.5Max
72.3%
GPT-6 AstraMax
72.0%
DeepSeek-V4.1-FlashMax
71.7%
Opus 5Max
71.4%
Gemini 3.8 FlashHigh
71.4%
FrontierSWE v2
34 open-ended engineering projects, from building compilers and simulators to optimizing inference and training research models. Each task gives an agent 20 hours and scores its result on the task's own metric, with partial credit.
Fable 5.1High
37.2%
GPT-6 AstraMax
29.9%
Opus 5High
27.3%
GPT-5.6 SolMax
20.2%
GLM-5.3Max
17.1%
Harvey LAB
An attorney-built benchmark of 1,749 real legal tasks (Main LAB and LAB: contracts) across 24 practice areas. Unlike typical legal QA benchmarks, it requires producing real work: memos, redlines, contracts, filings through an agentic loop.
Opus 5Max
17.8%
Kimi K3Max
14.9%
Fable 5Max
14.4%
Qwen3.8-MaxxHigh
11.9%
DeepSeek-V4-Pro-0813Max
11.4%
MedXpertQA MM
200 multimodal multiple-choice medical questions spread across 11 body systems. Each task requires multi-step reasoning over clinical images and patient details.
GPT-6 AstraMax
86.8%
Opus 5.5Max
85.7%
Gemini 3.8 FlashHigh
84.7%
Gemini 3.5 FlashHigh
83.5%
Gemini 3.7 FlashHigh
83.5%
ProgramBench
Tests whether software-engineering agents can rebuild complete programs from scratch given only a program and its documentation, matching a reference executable via end-to-end testing (100 tasks, CLI tools to FFmpeg/SQLite/PHP).
Opus 5.5Max
20.0%
Fable 5.1High
11.3%
Opus 5High
4.3%
GPT-6 SolMax
2.3%
Grok 4.6High
1.7%
SWE-bench Multilingual
A multilingual expansion for SWE-bench that tests whether LLMs can resolve 298 real-world GitHub issues in 42 repositories spanning nine programming languages.
DeepSeek-V4.1-FlashMax
98.2%
DeepSeek-V4-Pro-0813Max
96.4%
Opus 5Max
96.2%
Opus 5.5Max
95.5%
DeepSeek-V4-FlashMax
95.4%
Read the blog
The latest research and insights from the Mercor team.
Benchmarking methodology
How Mercor runs benchmarks to measure the frontier of intelligence.
Frequently Asked Questions
The Mercor AI Productivity Index (APEX) is a family of benchmarks that measure how effectively AI models and agents perform economically valuable tasks. It provides data-driven, real-world productivity metrics across high-value sectors, like software engineering, corporate law, investment banking, accounting, and management consulting. The suite includes benchmarks such as APEX-Agents, which evaluates long-horizon, multi-step agent workflows; APEX-SWE, focused on software engineering; APEX-Accounting, focused on agentic accounting tasks; and APEX-1, which evaluates single-turn expert knowledge work. Additional benchmarks will be introduced as APEX expands into new domains, data types, and workflows.
Rankings can change whenever a frontier model is released. New models are evaluated on APEX-Agents, APEX-SWE, APEX-Accounting and APEX-1 when they ship.
Practicing professionals from leading firms that the tasks simulate, including attorneys from Latham & Watkins, Skadden, and Cravath; consultants from McKinsey and BCG; bankers from Goldman Sachs, Morgan Stanley, and JPMorgan; and physicians from Brigham & Women's, UPenn, and Northwestern.
Yes, on the open subset. The eval harness is published on GitHub and sample tasks are on HuggingFace, so you can run the same scoring pipeline against your own model. The full task set stays private so that models can't be trained on it.
Frontier labs and model developers can request evaluation using this form.
Yes. Mercor licenses off-the-shelf datasets built by the same expert network. 50,000+ tasks across 30+ domains, with samples available the same day. Learn more about off-the-shelf data.