AI IQ
Subscribe

Toolathlon Cost Efficiency

Archived chart. Historical results combine original and Verified cohorts and are excluded from IQ. Retained for reference; scores are not a consistent current-model comparison.

Toolathlon Cost Efficiency
Toolathlon Cost Efficiency
Archived chart. Historical results combine original and Verified cohorts and are excluded from IQ. Retained for reference; scores are not a consistent current-model comparison.

How to read this chart

Toolathlon publishes no per-run cost, so this chart falls back to each model's estimated effective cost per 1M I/O tokens (a runtime estimate from measured or imputed token usage, not a published task cost). Explicit reasoning/nonreasoning siblings are connected where both are public; every other model is a standalone point. Up and to the left is better.

Data sources
Artificial AnalysisARC PrizeVals Index v2 Cost per TestVals.aiLLM StatsToolathlonLLM Stats Toolathlon
Archived chartToolathlon vs Effective CostArchived chart. Historical results combine original and Verified cohorts and are excluded from IQ. Retained for reference; scores are not a consistent current-model comparison.Data: Artificial Analysis, ARC Prize, Vals Index v2 Cost per Test +4 moreOpen chartArchived chartToolathlon Benchmark ScoresArchived chart. Historical results combine original and Verified cohorts and are excluded from IQ. Retained for reference; scores are not a consistent current-model comparison.Data: LLM Stats, Toolathlon, LLM Stats ToolathlonOpen chartArchived chartProofBench Benchmark ScoresArchived chart. Historical results combine benchmark versions and are excluded from IQ. Use the separately versioned ProofBench 1.1 for current comparisons.Data: Vals.aiOpen chartArchived chartFrontierSWE ScoresArchived chart. V1 Dominance retired from Composite IQ and Software Engineering; V2 mean@5 requires a separate calibration.Data: FrontierSWEOpen chartMore / ExperimentalSWE-Bench Verified Benchmark ScoresHistorical data. Vals archived cohort; retired from default Software Engineering domain. Each model's SWE-Bench Verified score. Color = provider.Data: Vals.ai, LLM StatsOpen chartArchived chartIOI Benchmark ScoresArchived chart. IOI V1 archived; V2 uses a different harness and 2024–2026 tasks.Data: Vals.ai IOIOpen chart