Aeon AI Risk Management
Model Economics Lab
Compare coding-agent capability, task cost and token usage before choosing a model. Start with current releases and the measured shortlist, then inspect sources and evidence tiers. Benchmark cost is not your cost per accepted production outcome.
From benchmark to buying decision
Include failed attempts, human review and rework in cost per accepted task. Compare hosted, private and hybrid routes on the same accepted workload. The linked methods are evaluation guidance, not new benchmark results.
Executive finding
Sol 6.1 XHigh scores 62.91 at $1.04 per evaluated task; Medium scores 61.41 at $0.70. Argon High scores 63.76 at $5.84 in a different native agent harness. Argon has restricted initial access and introductory pricing, followed by $4 input / $20 output per million tokens. Small score gaps are not established superiority. API costs are not subscription allowances.
Latest release evidence
The four additions use AA Coding Agent Index v1.5: Grok 4.7 XHigh 56.27 at $8.82 and 123.3k output tokens; Opus 5.5 Max 65.99 at $13.04 and 333.2k; GPT-6 Sol Max 56.66 at $2.99 and 62.2k; GPT-6 Luna Max 41.07 at $0.18 and 98.3k. Costs are per evaluated task. Opus includes safety recovery and fallback. Different agent harnesses, same benchmark suite; not rank-comparable with older index versions.
Subscription efficiency
Anthropic announced higher five-hour limits on eligible subscriptions separately from estimated typical-workload cost savings. No universal subscription-throughput multiplier is established. Maximum-effort coding economics need separate measurement.
Frontier economics
DeepSWE v1.1 gives Astra and Gemini 3.8 Flash the same 74 percent point estimate. Gemini averages $2.36 per task versus Astra's $6.52, while Astra uses fewer output tokens.
DeepSWE v1.1 common-harness view
The independent DeepSWE section retains pass rate, average task cost, output tokens, and agent steps from one mini-swe-agent harness. Use it for direct comparisons among current releases and measured shortlist anchors.
CursorBench 3.2 historical cross-check
This retained snapshot predates CursorBench 4.0. Do not directly compare percentages across versions or treat these older rows as the current shortlist.
Master plot
The horizontal axis is published or explicitly proxied task cost, the vertical axis is each point's published coding score in its native suite, and marker area represents published or proxied tokens. Filled circles are comparable measurements, diamonds are provisional cross-suite or proxy points, and hollow circles are modeled.
Reader views
Current releases, Popular models, Value challengers, and All / history separate the 16-point default from the complete retained dataset. All five observed Sol 6.1 efforts are available. Users can expand all effort levels, filter evidence, toggle trajectories, and change the cost scale.
Historical v1.3 measured anchors
Opus 5 xhigh reaches 66.74 at $8.23 per task. GPT-5.6 Sol max reaches 66.57 at $7.08. Grok 4.5 high reaches 64.44 at $2.59. Kimi K3 reaches 61.34 at $3.18. These are retained observations, not a current-release ranking.
Effort economics
Higher effort creates nonlinear token and cost growth. The last capability points can be valuable for ambiguous, long-horizon, or high-consequence work, but are usually inefficient for routine coding.
Modeled points
Where no comparable public run exists, Aeon uses neighboring model-family effort curves or a vendor-published effort curve. Every estimate is marked as modeled and is not presented as a benchmark result.
Limitations
Output tokens do not include every input, cache, retry, tool, and harness cost. Coding-agent token use can vary substantially by task and harness, so organizations should validate routing against their own repositories and acceptance tests.
Downloadable dataset
The full operating-point dataset is available in CSV and JSON with model, provider, effort, published score, native score metric, task cost and basis, tokens and token metric, evidence status, modeling basis, and source URL.
Dataset license and attribution
Aeon publishes this research compilation for evaluation and citation. Cite Aeon and link to this page when referencing the compilation. Underlying benchmark data and source materials remain subject to their publishers' terms. This notice does not relicense third-party material. Contact info@airiskmanagement.ca for redistribution or commercial reuse.
Update policy
Aeon adds current releases to the default plot, uses diamonds for newer-suite, cross-suite or proxy coordinates, and keeps displaced model observations in All / history.
Operating recommendation
Use a routing ladder that assigns cheaper effort to bounded tasks and reserves frontier settings for ambiguity, long dependency chains, and changes with high failure cost.