Set-Bench · agent benchmark

Cost, pass and latency, measured in the open.

Anthropic and Mistral across eight agent axes, n=10 per cell. The harness and every result JSON are public. Run it yourself, or pick it apart.

The caveats come before the numbers.

We host both Anthropic and Mistral, and this benchmark favours the cheaper one we also sell — treat it with the appropriate suspicion. The axes run against deterministic mock tools, so this measures loop mechanics and cost, not real-world tool quality. Pass is regex-pinned: a floor, not a quality grade. There is no quality column, because a cross-vendor quality score can't be made bias-free with available judges (why). And n=10 means point estimates with wide intervals — “100%” is 10/10, not a law.

The eight axes: multi-turn loops · sub-agent orchestration · memory-grounded reasoning · workflow composition · long-context tool use · back-tracking tool-chains · cron cold-starts · real-world strategy.

Matrix run 2026-05-30 · 8 axes × 9 models × n=10 (point estimates). Warm = with prompt-cache discount, cold = without. Deterministic mock tools — measures loop mechanics + cost, not real-world tool quality.

Multi-turn loop completion

Model Tag Pass Cost (warm) Cost (cold) Cache hit p50 p95
mistral-ministral-3b-2512 pinned 100% $0.00009 $0.00044 94% 1.6s 2.3s
mistral-ministral-8b-2512 pinned 100% $0.00013 $0.00066 94% 3.0s 3.7s
mistral-ministral-14b-2512 pinned 100% $0.00022 $0.00087 88% 5.3s 5.7s
mistral-large-2512 pinned 100% $0.00096 $0.00239 77% 12.0s 14.2s
anthropic-haiku-4-5 pinned 100% $0.00793 $0.00793 0% 3.4s 4.5s
mistral-medium-2604 pinned 100% $0.01281 $0.01686 30% 3.0s 3.3s
anthropic-sonnet-4-6 pinned 100% $0.01370 $0.02468 82% 8.3s 12.1s
anthropic-opus-4-7 pinned 100% $0.02486 $0.05377 90% 7.8s 12.0s
mistral-large-latest latest 80% $0.00107 $0.00191 57% 7.7s 18.6s

Sub-agent orchestration

Model Tag Pass Cost (warm) Cost (cold) Cache hit p50 p95
mistral-ministral-3b-2512 pinned 100% $0.00007 $0.00029 91% 1.5s 1.7s
mistral-ministral-8b-2512 pinned 100% $0.00011 $0.00043 89% 2.7s 3.8s
mistral-ministral-14b-2512 pinned 100% $0.00016 $0.00057 87% 3.4s 4.7s
mistral-large-2512 pinned 100% $0.00101 $0.00172 59% 7.7s 10.9s
mistral-medium-2604 pinned 100% $0.00471 $0.00582 31% 1.6s 2.3s
anthropic-haiku-4-5 pinned 100% $0.00588 $0.00588 0% 3.5s 6.2s
anthropic-sonnet-4-6 pinned 100% $0.01014 $0.01824 83% 8.0s 10.8s
anthropic-opus-4-7 pinned 100% $0.02519 $0.03994 77% 7.3s 8.2s
mistral-large-latest latest 90% $0.00090 $0.00163 64% 4.5s 19.1s

Memory-grounded reasoning

Model Tag Pass Cost (warm) Cost (cold) Cache hit p50 p95
mistral-ministral-3b-2512 pinned 100% $0.00006 $0.00034 94% 0.6s 0.8s
mistral-ministral-8b-2512 pinned 100% $0.00006 $0.00034 93% 0.5s 0.8s
mistral-ministral-14b-2512 pinned 100% $0.00008 $0.00045 93% 0.5s 0.6s
mistral-large-2512 pinned 100% $0.00048 $0.00118 68% 8.5s 9.8s
mistral-medium-2604 pinned 100% $0.00299 $0.00367 22% 0.8s 1.0s
anthropic-haiku-4-5 pinned 100% $0.00409 $0.00409 0% 1.9s 3.9s
anthropic-sonnet-4-6 pinned 100% $0.00443 $0.01189 95% 3.6s 4.9s
anthropic-opus-4-7 pinned 100% $0.01077 $0.02645 88% 3.4s 8.2s
mistral-large-latest latest 70% $0.00049 $0.00088 52% 1.5s 16.3s

Workflow composition

Model Tag Pass Cost (warm) Cost (cold) Cache hit p50 p95
mistral-ministral-3b-2512 pinned 100% $0.00013 $0.00074 95% 1.5s 3.6s
mistral-ministral-14b-2512 pinned 100% $0.00014 $0.00071 93% 1.6s 2.0s
mistral-ministral-8b-2512 pinned 100% $0.00014 $0.00084 95% 1.8s 2.2s
mistral-large-2512 pinned 100% $0.00065 $0.00145 70% 8.3s 10.5s
mistral-medium-2604 pinned 100% $0.00359 $0.00475 34% 1.1s 1.2s
anthropic-haiku-4-5 pinned 100% $0.00609 $0.00609 0% 3.1s 5.1s
anthropic-sonnet-4-6 pinned 100% $0.00787 $0.02088 94% 6.7s 8.6s
anthropic-opus-4-7 pinned 100% $0.02887 $0.04472 87% 7.0s 10.9s
mistral-large-latest latest 80% $0.00043 $0.00124 84% 2.9s 17.1s

Long-context with tools

Model Tag Pass Cost (warm) Cost (cold) Cache hit p50 p95
mistral-ministral-3b-2512 pinned 100% $0.00013 $0.00066 89% 0.5s 0.7s
mistral-ministral-8b-2512 pinned 100% $0.00020 $0.00100 89% 0.6s 0.7s
mistral-ministral-14b-2512 pinned 100% $0.00027 $0.00133 89% 1.0s 1.7s
mistral-large-latest latest 100% $0.00219 $0.00337 40% 1.3s 1.7s
mistral-medium-2604 pinned 100% $0.00324 $0.01033 80% 0.7s 2.8s
anthropic-haiku-4-5 pinned 100% $0.00444 $0.01713 96% 2.6s 4.9s
anthropic-sonnet-4-6 pinned 100% $0.01290 $0.05132 98% 5.0s 9.5s
anthropic-opus-4-7 pinned 100% $0.01725 $0.05638 99% 2.5s 19.6s
mistral-large-2512 pinned 80% $0.00092 $0.00269 75% 1.6s 16.8s

Tool-chain with back-track

Model Tag Pass Cost (warm) Cost (cold) Cache hit p50 p95
mistral-ministral-3b-2512 pinned 100% $0.00008 $0.00047 95% 0.9s 1.3s
mistral-ministral-8b-2512 pinned 100% $0.00011 $0.00071 95% 1.1s 2.0s
mistral-ministral-14b-2512 pinned 100% $0.00015 $0.00095 95% 1.2s 1.8s
mistral-large-2512 pinned 100% $0.00060 $0.00127 63% 7.7s 9.0s
mistral-medium-2604 pinned 100% $0.00640 $0.00760 19% 1.4s 1.5s
anthropic-sonnet-4-6 pinned 100% $0.00725 $0.02536 97% 7.9s 9.3s
anthropic-haiku-4-5 pinned 100% $0.00825 $0.00825 0% 3.7s 5.1s
anthropic-opus-4-7 pinned 100% $0.01611 $0.05407 94% 6.8s 9.0s
mistral-large-latest latest 80% $0.00036 $0.00108 80% 2.3s 17.2s

Cron task / cold-start

Model Tag Pass Cost (warm) Cost (cold) Cache hit p50 p95
mistral-ministral-3b-2512 pinned 100% $0.00004 $0.00023 91% 0.4s 0.7s
mistral-ministral-8b-2512 pinned 100% $0.00007 $0.00035 91% 0.5s 0.6s
mistral-ministral-14b-2512 pinned 100% $0.00013 $0.00046 81% 0.7s 1.3s
mistral-large-2512 pinned 100% $0.00053 $0.00118 63% 8.4s 8.6s
mistral-medium-2604 pinned 100% $0.00271 $0.00368 31% 0.7s 0.8s
anthropic-sonnet-4-6 pinned 100% $0.00381 $0.01163 96% 3.6s 4.4s
anthropic-haiku-4-5 pinned 100% $0.00417 $0.00417 0% 2.2s 3.9s
anthropic-opus-4-7 pinned 100% $0.00956 $0.02526 89% 3.4s 5.7s
mistral-large-latest latest 70% $0.00024 $0.00089 85% 1.4s 16.4s

Real-world grounded strategy

Model Tag Pass Cost (warm) Cost (cold) Cache hit p50 p95
mistral-ministral-3b-2512 pinned 100% $0.00006 $0.00026 92% 1.0s 1.8s
mistral-ministral-8b-2512 pinned 100% $0.00010 $0.00040 92% 2.0s 2.8s
mistral-ministral-14b-2512 pinned 100% $0.00013 $0.00053 92% 2.4s 2.8s
mistral-large-2512 pinned 100% $0.00081 $0.00148 62% 7.1s 11.4s
mistral-medium-2604 pinned 100% $0.00353 $0.00477 37% 1.3s 1.5s
anthropic-haiku-4-5 pinned 100% $0.00490 $0.00490 0% 3.7s 6.5s
anthropic-sonnet-4-6 pinned 100% $0.00832 $0.01615 93% 9.5s 11.0s
anthropic-opus-4-7 pinned 100% $0.01974 $0.03545 88% 8.6s 9.8s
mistral-large-latest latest 90% $0.00077 $0.00140 60% 4.4s 19.7s

A benchmark is only worth what its author is willing to lose by publishing it.

The cheaper model wins most of these cells, and we sell it. That is exactly why the harness, the raw JSON and the losing runs are all public: so you don't have to take our word for any of it. The full write-up — conflict of interest and all — is in the findings.

Cost is per task. Warm bills cache-read tokens at the published cache-read rate; cold applies no cache discount. Pinned snapshots (e.g. mistral-large-2512) are recommended over -latest tags, which Mistral rolls silently. Graded answer-quality is measured in the harness but not published here: a cross-vendor quality score can't be made bias-free with available judges; see the findings for that discussion.

Set-Bench is part of lynox, a source-available professional agent (Elastic License v2). The model-routing it informs is why we built it. Source on GitHub.