MODEL EVALUATION DASHBOARD

Claude Opus 5

Evaluating agent task completion, skill acceleration, latency, and token economics on 31 benchmark tasks.
Model: openrouter/anthropic/claude-opus-5 • Sampling: k=1 (62 runs total)

🌟 With Skills
100.0%
PASS RATE (31/31)
Pass rate achieved when the agent utilizes AtomisticSkills domain tools and workflows.
17m
MEAN LATENCY
Mean wall-clock execution time for the agent to complete the task with domain skills.
10.1k
MEAN OUT TOKENS
Mean output tokens generated by the LLM (total completion tokens, including reasoning/thinking tokens where applicable) when utilizing domain skills.
95.5%
CACHE HIT RATE
Percentage of input tokens served from provider KV cache during with-skills runs (Cached Tokens / Total Input Tokens).
⚖️ No Skills
80.6%
PASS RATE (25/31)
Baseline pass rate achieved when the agent attempts tasks using only general coding tools without domain skills.
19m
MEAN LATENCY
Mean wall-clock execution time for the agent without domain skills.
23.5k
MEAN OUT TOKENS
Mean output tokens generated without domain skills (total completion tokens, including reasoning/thinking tokens). Without structured skills, models frequently burn more tokens exploring.
90.0%
CACHE HIT RATE
Percentage of input tokens served from provider KV cache during baseline no-skills runs.
+19.4%
SKILL BOOST Δ
Absolute pass rate gain achieved over the no-skills baseline: (With-Skills Pass) - (No-Skills Pass).
$58.11
TOTAL COST (62 RUNS)
Total LLM inference cost computed from provider token pricing, incorporating cached input discounts.
Discipline Task Name With Skills No Skills All Solvers Time (With / No) Out Tokens (With / No) Action
chemistry bde-weak-bonds 1/1 0/1 1/2 (50.0%) 83m/34m 22.8k/21.2k View Details →
chemistry conformer-boltzmann-ranking 1/1 0/1 1/2 (50.0%) 60m/43m 33.4k/41.7k View Details →
chemistry gas-thermochemistry-equilibrium 1/1 1/1 2/2 (100.0%) 176s/425s 5.0k/7.4k View Details →
chemistry ghs-hazard-summary 1/1 0/1 1/2 (50.0%) 87s/346s 2.2k/14.0k View Details →
chemistry ir-spectrum-match 1/1 1/1 2/2 (100.0%) 58s/76s 1.9k/3.4k View Details →
chemistry mof-dac-screening 1/1 1/1 2/2 (100.0%) 15m/37m 12.0k/19.4k View Details →
chemistry nmr-reaction-kinetics 1/1 1/1 2/2 (100.0%) 395s/24m 7.4k/60.3k View Details →
drug-discovery admet-lead-triage 1/1 1/1 2/2 (100.0%) 80s/69s 2.9k/3.1k View Details →
drug-discovery docking-microstate-enrichment 1/1 1/1 2/2 (100.0%) 443s/517s 25.0k/33.7k View Details →
drug-discovery ecfp-analog-diversity 1/1 1/1 2/2 (100.0%) 58s/46s 1.6k/1.8k View Details →
drug-discovery ligand-box-definition 1/1 1/1 2/2 (100.0%) 57s/56s 2.6k/3.4k View Details →
drug-discovery ligand-md-stability 1/1 1/1 2/2 (100.0%) 115s/118s 5.5k/5.0k View Details →
drug-discovery pose-quality-filter 1/1 1/1 2/2 (100.0%) 178s/195s 2.1k/3.5k View Details →
drug-discovery symmetry-redocking-rmsd 1/1 1/1 2/2 (100.0%) 118s/91s 4.7k/4.8k View Details →
machine-learning committee-uncertainty-flagging 1/1 1/1 2/2 (100.0%) 143s/128s 2.3k/1.9k View Details →
machine-learning mlip-error-benchmark 1/1 1/1 2/2 (100.0%) 208s/432s 4.5k/8.2k View Details →
materials-science camgsi-elasticity-vrh 1/1 1/1 2/2 (100.0%) 428s/15m 11.3k/24.9k View Details →
materials-science co-adsorption-cu111 1/1 1/1 2/2 (100.0%) 397s/542s 9.5k/10.0k View Details →
materials-science convex-hull-stability 1/1 0/1 1/2 (50.0%) 37m/45m 19.3k/14.3k View Details →
materials-science crconi-order-disorder 1/1 1/1 2/2 (100.0%) 71m/96m 20.5k/35.4k View Details →
materials-science electrochemical-window 1/1 0/1 1/2 (50.0%) 22m/26m 15.7k/33.7k View Details →
materials-science li-qha-simulation 1/1 1/1 2/2 (100.0%) 430s/29m 12.7k/51.4k View Details →
materials-science lifepo4-intercalation-voltage 1/1 1/1 2/2 (100.0%) 30m/397s 8.6k/2.9k View Details →
materials-science mgo-vacancy-energy 1/1 1/1 2/2 (100.0%) 16m/12m 15.0k/7.0k View Details →
materials-science ni3al-surface-energy 1/1 1/1 2/2 (100.0%) 34m/29m 19.0k/22.7k View Details →
materials-science nist-janaf-query 1/1 1/1 2/2 (100.0%) 64s/178s 1.4k/3.8k View Details →
materials-science polymorph-free-energy 1/1 1/1 2/2 (100.0%) 79m/92m 18.7k/244.8k View Details →
materials-science si-eos-fit 1/1 1/1 2/2 (100.0%) 155s/141s 3.3k/2.3k View Details →
materials-science sic-thermal-conductivity 1/1 0/1 1/2 (50.0%) 479s/529s 8.2k/8.0k View Details →
materials-science synthesis-precursor-recommendation 1/1 1/1 2/2 (100.0%) 129s/515s 3.0k/6.7k View Details →
materials-science xrd-mixture-phase-fit 1/1 1/1 2/2 (100.0%) 16m/15m 11.1k/27.2k View Details →