FIBRE

opus-5

Anthropic · high effort · claude-opus-5

Ranked 1 of 5 overall on 200 tasks. Strongest on monitoring at 97.5, weakest on credit analysis at 86.4.

Score
91.3
rank 1 of 5
Latency
143s
median per task
Cost
$1.16
per task at list prices

Capability profile

Mean score per category on question-answering, 0–100.
CreditMonitorStructuredResearchDiscovery

Score by category

5 categories, 150 tasks on question-answering.
Credit Analysis86.4 · 61
Monitoring97.5 · 20
Structured Products90.8 · 17
Research Intelligence89.9 · 10
Discovery & Prediction97.2 · 2

Where it sits

opus-5 against the rest of the board. Everything else is drawn back so the one model reads.
No model here.Better on both axes at once.$0.01$0.02$0.05$0.1$0.2$0.5$165758595Cost per task · better ←Score · better ↑Best per taskopus-5
opus-5 on the frontier — no model beats it on bothFrontier · 3 models nothing beats on both

Best per task is the diamond: for each of the 200 tasks every model attempted, the highest score any of them got, averaged — 95.0 against 91.3 for opus-5 used on everything. Nobody can build it. The choice is made with the result in hand, which a router does not have when it has to choose, so it marks the edge of what having 5 different models is worth rather than a score anyone can reach. It is also flattered by noise — the highest of 5 measurements rises with the count even when the models behind them do not improve — so it will drift up as models are added and is not comparable between boards with different numbers of them. 2 tasks are left out of it, for not having been attempted by every model. Its cost is measured the way the board measures a model’s, on the question-answering track that holds more of the tasks.

How it works when given tools

Behaviour across 150 agentic-research runs.
Delivered an answer
100%
of runs produced a deliverable
Mean steps
20.4
tool calls per run
Tools used per run
fetch_url 16.5sec_search 1.8python_exec 1.7web_search 0.3
How runs ended
final answer 70%max steps 30%

Where it lost the most

The lowest-scoring tasks on question-answering, with the rubric gates that fired where they are known.
PARTIAL
New Issue Evaluation
Credit Analysis · new issue, high yield, fair value
23.1
PARTIAL
Fcf Debt Service
financial_foundations · fcf, normalization, delevering
28.1
PARTIAL
Trade Idea Extraction
Research Intelligence · portfolio strategy, no trade ideas, vanguard
30.0
PARTIAL
Relative Value
Credit Analysis · RV, REIT, recommendation
37.8
PARTIAL
Relative Value
Credit Analysis · RV, REIT, office
40.0