unbiased ai

Pareto 26.10

Pareto 26.10 model card

Pareto is Unbiased’s blended AI model: it selects frontier and open models for each request and blends their outputs into one answer. Release notes: Pareto 26.10 is out of preview.

Benchmarks

DeepSWE

Cost per task, USD · log scale

DeepSWE v1.1 · 3 reported results · Score (%) and USD mean per task
Pareto 26.10Oct 1, 202669.9%$0.24
Fable 5Aug 15, 202670.0%$13.50
Pareto 26.9Sep 20, 202670.0%$0.29

Bars use one linear cost scale per benchmark.

Evaluation details
  • Preliminary comparison. Pareto 26.10 results are from October 1, 2026 runs and may change before final publication. Results from our other runs are transcribed from a September 21, 2026 comparison and are not independently validated. Denominators and cost methodology require confirmation.
  • Run dates: October 1, 2026 for Pareto 26.10; September 20, 2026 for Pareto 26.9; August 15, 2026 for Fable 5. The Pareto 26.9 and Fable 5 DeepSWE results use a 30-task slice, not the full DeepSWE v1.1 set. Pareto 26.9’s HLE result was reported as Humanity’s Last Exam, without a text-only qualifier.
  • Each point is one reported result; no performance curves are interpolated. Costs are reported mean USD per task, not token prices. Missing results stay missing and never plot as zero.
  • Axes fit the results shown: cost on a log scale, score over at least 30 points. The orange step line shows the best score reached at or below each cost.
  • Grey points are other labs’ published results, from the DeepSWE and Terminal-Bench leaderboards, Artificial Analysis, Epoch AI, OpenAI’s GPT-6 Sol and Luna and GPT-6.1 Sol announcements, and Anthropic’s Claude Sonnet 5.5 announcement and system card. They use their own task sets and harnesses, so they are not directly comparable with our runs. Results without a published cost sit on the rail beside the chart, at their score.
  • Pareto 26.9 is the previous release, shown for comparison. Fable 5 is a historical comparator, not a model in the published scores. We have not run GPT-6.1 Sol, GPT-6 Luna or Claude Sonnet 5.5 ourselves. Their points are published results from their labs and independent evaluators. Results from these runs for third-party model-selection services are not shown.
  • Published competitor results come from separate evaluators, not our preliminary runs. Each competitor score is paired only with its source’s task cost, never Pareto’s task cost.

Trade-off frontier

The same preliminary Pareto 26.10 runs as the chart above, drawn as static charts with the homepage score table’s models wherever a source publishes both a score and a cost per task. GPQA-Diamond is left out: no other model in that table has a published cost per task for it. At least one model scores higher than Pareto 26.10 on each of them: where other models score higher.

Terminal-Bench 4.0 Agentic terminal use

% solved against $/task. Up and left is better.

Terminal-Bench 4.0: % solved against cost per taskPareto 26.10 scores 50.8% at $0.48 per task. Other models: Fable 5.1 55.1% at $15.78; GPT-6 Astra 59.6% at $5.86; DeepSeek V4.1 Flash 26.8% at $1.16; GPT-6.1 Sol 56.1% at $1.82; GPT-6 Luna 12.6% at $0.24; Claude Sonnet 5.5 70.6% at $12.54. The dotted line marks the best score reached at or below each cost: GPT-6 Luna, Pareto 26.10, GPT-6.1 Sol, GPT-6 Astra, Claude Sonnet 5.5.Terminal-Bench 4.0: % solved against cost per taskPareto 26.10 scores 50.8% at $0.48 per task. Other models: Fable 5.1 55.1% at $15.78; GPT-6 Astra 59.6% at $5.86; DeepSeek V4.1 Flash 26.8% at $1.16; GPT-6.1 Sol 56.1% at $1.82; GPT-6 Luna 12.6% at $0.24; Claude Sonnet 5.5 70.6% at $12.54. The dotted line marks the best score reached at or below each cost: GPT-6 Luna, Pareto 26.10, GPT-6.1 Sol, GPT-6 Astra, Claude Sonnet 5.5.
Pareto 26.10: preliminary October 1, 2026 run; may change before final publication. Other models: results published as of October 1, 2026 by Artificial Analysis and Anthropic, run with their own task sets and harnesses, so not directly comparable with our runs. Full score table · Method
Show the numbers
Terminal-Bench 4.0: % solved and mean cost per task
Model% solved$/taskSource
Claude Sonnet 5.570.6%$12.54Anthropic
GPT-6 Astra59.6%$5.86Artificial Analysis
GPT-6.1 Sol56.1%$1.82Artificial Analysis
Fable 5.155.1%$15.78Artificial Analysis
Pareto 26.1050.8%$0.48Unbiased, preliminary October 1, 2026 run
DeepSeek V4.1 Flash26.8%$1.16Artificial Analysis
GPT-6 Luna12.6%$0.24Artificial Analysis

DeepSWE v1.1 Agentic coding

% solved against $/task. Up and left is better.

DeepSWE v1.1: % solved against cost per taskPareto 26.10 scores 69.9% at $0.24 per task. Other models: GPT-6 Astra 74.0% at $4.43; GPT-6.1 Sol 75.2% at $0.65; GPT-6 Luna 66.6% at $0.22. The dotted line marks the best score reached at or below each cost: GPT-6 Luna, Pareto 26.10, GPT-6.1 Sol.DeepSWE v1.1: % solved against cost per taskPareto 26.10 scores 69.9% at $0.24 per task. Other models: GPT-6 Astra 74.0% at $4.43; GPT-6.1 Sol 75.2% at $0.65; GPT-6 Luna 66.6% at $0.22. The dotted line marks the best score reached at or below each cost: GPT-6 Luna, Pareto 26.10, GPT-6.1 Sol.
Pareto 26.10: preliminary October 1, 2026 run; may change before final publication. Other models: results published as of October 1, 2026 by DeepSWE leaderboard and OpenAI, run with their own task sets and harnesses, so not directly comparable with our runs. Not plotted: Claude Sonnet 5.5 (score published, no cost per task); Fable 5.1 and DeepSeek V4.1 Flash (no score reported). Full score table · Method
Show the numbers
DeepSWE v1.1: % solved and mean cost per task
Model% solved$/taskSource
GPT-6.1 Sol75.2%$0.65OpenAI
GPT-6 Astra74.0%$4.43DeepSWE leaderboard
Pareto 26.1069.9%$0.24Unbiased, preliminary October 1, 2026 run
GPT-6 Luna66.6%$0.22OpenAI

HLE (text-only) Expert reasoning

% solved against $/task. Up and left is better.

HLE (text-only): % solved against cost per taskPareto 26.10 scores 49.9% at $0.008 per task. Other models: Fable 5.1 59.1% at $1.59; GPT-6 Astra 54.7% at $0.38; DeepSeek V4.1 Flash 39.2% at $0.042; GPT-6.1 Sol 52.9% at $0.078; GPT-6 Luna 38.5% at $0.012; Claude Sonnet 5.5 55.0% at $0.54. The dotted line marks the best score reached at or below each cost: Pareto 26.10, GPT-6.1 Sol, GPT-6 Astra, Claude Sonnet 5.5, Fable 5.1.HLE (text-only): % solved against cost per taskPareto 26.10 scores 49.9% at $0.008 per task. Other models: Fable 5.1 59.1% at $1.59; GPT-6 Astra 54.7% at $0.38; DeepSeek V4.1 Flash 39.2% at $0.042; GPT-6.1 Sol 52.9% at $0.078; GPT-6 Luna 38.5% at $0.012; Claude Sonnet 5.5 55.0% at $0.54. The dotted line marks the best score reached at or below each cost: Pareto 26.10, GPT-6.1 Sol, GPT-6 Astra, Claude Sonnet 5.5, Fable 5.1.
Pareto 26.10: preliminary October 1, 2026 run; may change before final publication. Other models: results published as of October 1, 2026 by Artificial Analysis, run with their own task sets and harnesses, so not directly comparable with our runs. Full score table · Method
Show the numbers
HLE (text-only): % solved and mean cost per task
Model% solved$/taskSource
Fable 5.159.1%$1.59Artificial Analysis, no tools
Claude Sonnet 5.555.0%$0.54Artificial Analysis, no tools
GPT-6 Astra54.7%$0.38Artificial Analysis, no tools
GPT-6.1 Sol52.9%$0.078Artificial Analysis, no tools
Pareto 26.1049.9%$0.008Unbiased, preliminary October 1, 2026 run
DeepSeek V4.1 Flash39.2%$0.042Artificial Analysis, no tools
GPT-6 Luna38.5%$0.012Artificial Analysis, no tools

Details and pricing

Pareto accepts text and image inputs. Use pareto as the model identifier. The homepage score table compares Pareto with Fable 5.1, GPT-6 Astra, DeepSeek V4.1 Flash, GPT-6.1 Sol, GPT-6 Luna, and Claude Sonnet 5.5. The chart also includes published results for Claude Opus 5.5 on HLE and Terminal-Bench 4.0.

Per million tokens: $0.80 input, $0.03 cached input, and $3.20 output. Actual spend depends on token usage and cache hits.

Pricing · API setup · Pareto 26.10 release hub · Pareto vs Fable 5

Test it against your own workload.
Get started with Unbiased