FIBRE

sonnet-5

Anthropic · high effort · claude-sonnet-5

Ranked 2 of 5 overall on 202 tasks. Strongest on monitoring at 93.2, weakest on credit analysis at 83.7.

Score
86.3
rank 2 of 5
Latency
86.1s
median per task
Cost
$0.519
per task at list prices

Capability profile

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

Score by category

5 categories, 152 tasks on question-answering.
Credit Analysis83.7 · 62
Monitoring93.2 · 20
Structured Products86.7 · 18
Research Intelligence84.6 · 10
Discovery & Prediction85.6 · 2

Where it sits

sonnet-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 tasksonnet-5
sonnet-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
16.3
tool calls per run
Tools used per run
fetch_url 11.8python_exec 1.9sec_search 1.9web_search 0.7
How runs ended
final answer 81%max steps 19%

Where it lost the most

The lowest-scoring tasks on question-answering, with the rubric gates that fired where they are known.
FAIL
MBS Prepayment
Structured Products · structured, MBS, dollar roll
penalty: Does not assume the dollar roll is always cheap or always expensive. The implied financin…
0.0
PARTIAL
Trade Idea Extraction
Research Intelligence · portfolio strategy, no trade ideas, vanguard
30.0
PARTIAL
Fcf Debt Service
financial_foundations · fcf, normalization, delevering
38.6
PARTIAL
ABS Waterfall
Structured Products · structured, ABS, waterfall
42.2
PARTIAL
Relative Value
Credit Analysis · RV, technology, revenue quality
45.2