← Back to Cross-Model Leaderboard
MODEL EVALUATION DASHBOARD

GLM-5.3 Flash

Evaluating agent task completion, skill acceleration, latency, and token economics on 31 benchmark tasks.
Model: openai/glm-5.3-flash • Sampling: k=1 (62 runs total)

🌟 With Skills
87.1%
PASS RATE (27/31)
Pass rate achieved when the agent utilizes AtomisticSkills domain tools and workflows.
32m
MEAN LATENCY
Mean wall-clock execution time for the agent to complete the task with domain skills.
40.8k
MEAN OUT TOKENS
Mean output tokens generated by the LLM (total completion tokens, including reasoning/thinking tokens where applicable) when utilizing domain skills.
96.2%
CACHE HIT RATE
Percentage of input tokens served from provider KV cache during with-skills runs (Cached Tokens / Total Input Tokens).
⚖️ No Skills
77.4%
PASS RATE (24/31)
Baseline pass rate achieved when the agent attempts tasks using only general coding tools without domain skills.
41m
MEAN LATENCY
Mean wall-clock execution time for the agent without domain skills.
63.2k
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.
91.6%
CACHE HIT RATE
Percentage of input tokens served from provider KV cache during baseline no-skills runs.
+9.7%
SKILL BOOST Δ
Absolute pass rate gain achieved over the no-skills baseline: (With-Skills Pass) - (No-Skills Pass).
$6.68
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%) 102m/114m 89.6k/141.0k View Details →
chemistry conformer-boltzmann-ranking 1/1 0/1 1/2 (50.0%) 34m/100m 58.7k/123.0k View Details →
chemistry gas-thermochemistry-equilibrium 1/1 0/1 1/2 (50.0%) 15m/15m 27.4k/28.4k View Details →
chemistry ghs-hazard-summary 1/1 0/1 1/2 (50.0%) 501s/23m 13.6k/52.1k View Details →
chemistry ir-spectrum-match 1/1 1/1 2/2 (100.0%) 536s/13m 18.9k/29.4k View Details →
chemistry mof-dac-screening 0/1 1/1 1/2 (50.0%) 54m/122m 74.2k/199.7k View Details →
chemistry nmr-reaction-kinetics 0/1 1/1 1/2 (50.0%) 472s/13m 10.7k/27.0k View Details →
drug-discovery admet-lead-triage 1/1 1/1 2/2 (100.0%) 239s/258s 8.9k/8.7k View Details →
drug-discovery docking-microstate-enrichment 1/1 0/1 1/2 (50.0%) 38m/50m 90.9k/114.0k View Details →
drug-discovery ecfp-analog-diversity 1/1 1/1 2/2 (100.0%) 220s/215s 6.6k/7.4k View Details →
drug-discovery ligand-box-definition 1/1 1/1 2/2 (100.0%) 365s/279s 15.3k/7.6k View Details →
drug-discovery ligand-md-stability 1/1 1/1 2/2 (100.0%) 501s/21m 19.3k/37.0k View Details →
drug-discovery pose-quality-filter 1/1 1/1 2/2 (100.0%) 306s/307s 8.3k/7.8k View Details →
drug-discovery symmetry-redocking-rmsd 1/1 1/1 2/2 (100.0%) 226s/362s 7.5k/11.3k View Details →
machine-learning committee-uncertainty-flagging 1/1 1/1 2/2 (100.0%) 356s/385s 9.7k/9.6k View Details →
machine-learning mlip-error-benchmark 1/1 1/1 2/2 (100.0%) 477s/413s 10.2k/9.3k View Details →
materials-science camgsi-elasticity-vrh 1/1 1/1 2/2 (100.0%) 80m/65m 93.1k/201.1k View Details →
materials-science co-adsorption-cu111 1/1 1/1 2/2 (100.0%) 56m/54m 71.1k/58.1k View Details →
materials-science convex-hull-stability 1/1 0/1 1/2 (50.0%) 20m/60m 28.7k/97.7k View Details →
materials-science crconi-order-disorder 1/1 1/1 2/2 (100.0%) 194m/138m 224.9k/168.7k View Details →
materials-science electrochemical-window 1/1 1/1 2/2 (100.0%) 54m/56m 66.1k/85.6k View Details →
materials-science li-qha-simulation 0/1 0/1 0/2 (0.0%) 39m/43m 63.9k/55.6k View Details →
materials-science lifepo4-intercalation-voltage 1/1 1/1 2/2 (100.0%) 25m/27m 21.0k/31.5k View Details →
materials-science mgo-vacancy-energy 0/1 1/1 1/2 (50.0%) 23m/19m 31.1k/29.6k View Details →
materials-science ni3al-surface-energy 1/1 1/1 2/2 (100.0%) 50m/89m 53.6k/121.3k View Details →
materials-science nist-janaf-query 1/1 1/1 2/2 (100.0%) 108s/160s 2.4k/4.8k View Details →
materials-science polymorph-free-energy 1/1 0/1 1/2 (50.0%) 65m/120m 62.0k/156.2k View Details →
materials-science si-eos-fit 1/1 1/1 2/2 (100.0%) 10m/11m 15.1k/17.2k View Details →
materials-science sic-thermal-conductivity 1/1 1/1 2/2 (100.0%) 20m/26m 31.9k/33.2k View Details →
materials-science synthesis-precursor-recommendation 1/1 1/1 2/2 (100.0%) 141s/34m 3.5k/64.1k View Details →
materials-science xrd-mixture-phase-fit 1/1 1/1 2/2 (100.0%) 22m/15m 27.7k/22.6k View Details →