Rankings / inception-ai
Mercury 2
proprietaryreleased 2026-02-20
BenchAtlas Index
as of 2026-09-11
base configuration
rank #315
7 families · 4 categories · medium
Benchmark evidence
23 results
agentic coding
| τ²-Bench | 70.8 % | independent | Artificial Analysis | |
| τ²-Bench subset=banking | 9.5 % | independent | Artificial Analysis |
coding
| SciCode | 37.7 % | independent | Artificial Analysis |
external indices
| AA Coding Index | 31.1 points | independent | Artificial Analysis | |
| Intelligence Index v4.1 | 11.5 points | independent | Artificial Analysis |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1393.7 1372.7–1414.7 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1383.8 1365.9–1401.8 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1372.3 1350.4–1394.2 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1370.1 1353.2–1387.1 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1360.2 1346.3–1374.1 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1346.5 1335.8–1357.2 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1342.7 1316.7–1368.7 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1327.2 1306.8–1347.5 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1323.8 1303.8–1343.8 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1322.5 1308.9–1336.1 | community | LMArena Leaderboard Dataset | |
| Industry Entertainment And Sports And Media (style control)older version arena=text · category=industry_entertainment_and_sports_and_media · style_control=true | 1315.5 1292.6–1338.3 | community | LMArena Leaderboard Dataset | |
| Industry Writing And Literature And Language (style control)older version arena=text · category=industry_writing_and_literature_and_language · style_control=true | 1310.5 1287.9–1333.0 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1300.2 1273.4–1327.1 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1299.4 1283.3–1315.4 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | 77.0 % | independent | Artificial Analysis | |
| Humanity's Last Exam implementation=artificial-analysis | 17.1 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | 43.7 % | independent | Artificial Analysis | |
| IFBench | 69.8 % | independent | Artificial Analysis |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + Mercury 2 | Terminal-Bench 2.1 | 27.3 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + Mercury 2 | Terminal-Bench Hard | 26.5 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.