MODEL EVALUATION DASHBOARD

GPT-5.6 Sol

Evaluating agent task completion, skill acceleration, latency, and token economics on 31 benchmark tasks.
Model: openai/gpt-5.6-sol • Sampling: k=1 (62 runs total)

🌟 With Skills
96.8%
PASS RATE (30/31)
Pass rate achieved when the agent utilizes AtomisticSkills domain tools and workflows.
13m
MEAN LATENCY
Mean wall-clock execution time for the agent to complete the task with domain skills.
11.0k
MEAN OUT TOKENS
Mean output tokens generated by the LLM (total completion tokens, including reasoning/thinking tokens where applicable) when utilizing domain skills.
97.8%
CACHE HIT RATE
Percentage of input tokens served from provider KV cache during with-skills runs (Cached Tokens / Total Input Tokens).
⚖️ No Skills
83.9%
PASS RATE (26/31)
Baseline pass rate achieved when the agent attempts tasks using only general coding tools without domain skills.
14m
MEAN LATENCY
Mean wall-clock execution time for the agent without domain skills.
11.4k
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.
97.4%
CACHE HIT RATE
Percentage of input tokens served from provider KV cache during baseline no-skills runs.
+12.9%
SKILL BOOST Δ
Absolute pass rate gain achieved over the no-skills baseline: (With-Skills Pass) - (No-Skills Pass).
$76.93
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 1/1 2/2 (100.0%) 68m/11m 16.4k/20.0k View Details →
chemistry conformer-boltzmann-ranking 1/1 0/1 1/2 (50.0%) 527s/26m 11.6k/19.7k View Details →
chemistry gas-thermochemistry-equilibrium 1/1 1/1 2/2 (100.0%) 91s/174s 5.2k/7.1k View Details →
chemistry ghs-hazard-summary 1/1 0/1 1/2 (50.0%) 56s/109s 3.3k/8.1k View Details →
chemistry ir-spectrum-match 1/1 1/1 2/2 (100.0%) 100s/106s 5.6k/8.0k View Details →
chemistry mof-dac-screening 1/1 1/1 2/2 (100.0%) 341s/324s 13.0k/12.3k View Details →
chemistry nmr-reaction-kinetics 1/1 1/1 2/2 (100.0%) 379s/236s 19.7k/13.4k View Details →
drug-discovery admet-lead-triage 1/1 1/1 2/2 (100.0%) 47s/43s 3.5k/3.8k View Details →
drug-discovery docking-microstate-enrichment 1/1 1/1 2/2 (100.0%) 210s/209s 18.1k/20.5k View Details →
drug-discovery ecfp-analog-diversity 1/1 1/1 2/2 (100.0%) 36s/26s 1.8k/1.9k View Details →
drug-discovery ligand-box-definition 1/1 1/1 2/2 (100.0%) 63s/39s 4.8k/3.1k View Details →
drug-discovery ligand-md-stability 1/1 1/1 2/2 (100.0%) 126s/101s 10.3k/9.0k View Details →
drug-discovery pose-quality-filter 1/1 1/1 2/2 (100.0%) 75s/71s 7.4k/4.7k View Details →
drug-discovery symmetry-redocking-rmsd 1/1 1/1 2/2 (100.0%) 65s/40s 3.9k/2.7k View Details →
machine-learning committee-uncertainty-flagging 1/1 1/1 2/2 (100.0%) 83s/76s 4.8k/3.2k View Details →
machine-learning mlip-error-benchmark 1/1 1/1 2/2 (100.0%) 101s/91s 5.6k/5.8k View Details →
materials-science camgsi-elasticity-vrh 1/1 1/1 2/2 (100.0%) 383s/368s 11.3k/14.4k View Details →
materials-science co-adsorption-cu111 1/1 1/1 2/2 (100.0%) 33m/504s 18.7k/14.8k View Details →
materials-science convex-hull-stability 1/1 0/1 1/2 (50.0%) 275s/26m 9.8k/21.6k View Details →
materials-science crconi-order-disorder 1/1 1/1 2/2 (100.0%) 57m/187m 35.0k/36.5k View Details →
materials-science electrochemical-window 1/1 1/1 2/2 (100.0%) 33m/383s 18.1k/11.9k View Details →
materials-science li-qha-simulation 0/1 0/1 0/2 (0.0%) 464s/283s 19.4k/14.2k View Details →
materials-science lifepo4-intercalation-voltage 1/1 0/1 1/2 (50.0%) 356s/96s 6.3k/3.5k View Details →
materials-science mgo-vacancy-energy 1/1 1/1 2/2 (100.0%) 217s/198s 8.3k/9.4k View Details →
materials-science ni3al-surface-energy 1/1 1/1 2/2 (100.0%) 474s/12m 10.7k/13.7k View Details →
materials-science nist-janaf-query 1/1 1/1 2/2 (100.0%) 31s/24s 1.5k/905 View Details →
materials-science polymorph-free-energy 1/1 1/1 2/2 (100.0%) 108m/90m 35.9k/34.6k View Details →
materials-science si-eos-fit 1/1 1/1 2/2 (100.0%) 73s/97s 3.6k/4.7k View Details →
materials-science sic-thermal-conductivity 1/1 1/1 2/2 (100.0%) 14m/358s 13.4k/10.8k View Details →
materials-science synthesis-precursor-recommendation 1/1 1/1 2/2 (100.0%) 54s/102s 3.5k/5.4k View Details →
materials-science xrd-mixture-phase-fit 1/1 1/1 2/2 (100.0%) 364s/317s 11.8k/13.0k View Details →