ModelSpec is an analysis of alternatives for AI models: it decides which models fit a job from your requirements, sourced benchmarks and real cost, and shows its work.

Gemini 3.7 Flash vs Gemini 3.8 Flash for Coding agent on a budget, as of 2026-09-23

Find an active coding model with enough context while keeping one task at or under $0.05.

Worked example as of 2026-09-23, from the public data image.

What the evidence says

The evidence can't separate them for this job.

Gemini 3.8 Flash has a 38% chance of matching or beating Gemini 3.7 Flash on this job's objective.

probability bands: a model joins the leader when P(its score >= the leader's) >= 0.25 under the score posteriors; a weighted capability with an 80% interval wider than 2.8 is not enough evidence

Decision status: partial. P(best) and score intervals retain the full ranked lineup for this job, including models beyond this pair and models with thin evidence. Models with unknown objective values remain unranked and are outside this probability. P(best) is not a head-to-head probability.

Scores and score intervals use the objective's dimensionless normalised units. Cost per task is in USD for the selected offering and the applied spec's task size. When task size is omitted, the engine uses its documented default. Unavailable means the engine returned no value.

Model	Score	Score interval	P(best), ranked job lineup	Cost per task, USD	Selected offering: provider / region / tier	Capability estimates and intervals
Gemini 3.7 Flash	0.6	[-1.248386, 2.448386]	64%	0.045	google-gemini-api / global / standard	software_engineering: 0.099771765; interval [-0.580250011, 0.779793541]; benchmarks 6; direct benchmarks 2
Gemini 3.8 Flash	0.0	[-1.549939, 1.549939]	36%	0.045	google-gemini-api / global / standard	software_engineering: -0.120968438; interval [-0.69119135, 0.449254473]; benchmarks 8; direct benchmarks 3

At most $0.05 a task; coding still ranked.

Requirements

model.class = text-generator: Coding work needs a model that generates text and code.
model.lifecycle = active: An active model is still supported by its lab or provider.
model.context_window >= 200000: A large repository needs room for code, tests, and instructions.
offering.cost_per_task <= 0.05: The offering must stay within the per-task budget.

Preferences

software_engineering: Prefer stronger evidence on real software-engineering tasks.
-offering.cost_per_task: Among qualifying offerings, prefer the cheaper task.

Applied template spec

spec_version

where

model.class = text-generator
model.lifecycle = active
model.context_window >= 200000
offering.cost_per_task <= 0.05

optimize

weights

software_engineering: 0.6
-offering.cost_per_task: 0.4

Evidence for Gemini 3.7 Flash

Benchmark	Version	Measurement	Unit	Published interval	Evidence date	Measurement conditions	Provenance
arena_sc_coding	text_style_control / coding, latest split, revision 1880dbebff5b	1520.59	Arena score (Elo scale)	Unavailable	2026-09-13	Effort: Unavailable Subcategory: Unavailable Harness: Unavailable Measured by: independent_evaluator Sample size: Unavailable	Source
arena_sc_industry_software_it_services	text_style_control / industry_software_and_it_services, latest split, revision 1880dbebff5b	1511.67	Arena score (Elo scale)	Unavailable	2026-09-13	Effort: Unavailable Subcategory: Unavailable Harness: Unavailable Measured by: independent_evaluator Sample size: Unavailable	Source
arena_webdev	webdev / overall, latest split, revision 1880dbebff5b	1594.56	Arena score (Elo scale)	Unavailable	2026-09-23	Effort: Unavailable Subcategory: Unavailable Harness: Unavailable Measured by: independent_evaluator Sample size: Unavailable	Source
deepswe_v1_1	DeepSWE v1.1, pass@1, mini-swe-agent	65.27	percent	Unavailable	2026-09-30	Effort: high Subcategory: Unavailable Harness: unregistered Measured by: benchmark_author Sample size: Unavailable	Source
frontiercode_v1_1	FrontierCode 1.1, main score (Mean@5)	43.6	percent	Unavailable	2026-09-30	Effort: medium Subcategory: Unavailable Harness: unregistered Measured by: benchmark_author Sample size: Unavailable	Source
terminal_bench_v4_0	Terminal-Bench 4.0	11.21	percent	Unavailable	2026-08-13	Effort: high Subcategory: Unavailable Harness: unregistered Measured by: benchmark_author Sample size: Unavailable	Source

Missing facts for Gemini 3.7 Flash

model.hardware_fit_indeterminate: unknown
model.languages: unknown
model.parameters_total: unknown
origin.base_lineage: not_disclosed
origin.weights_hosting: not_disclosed
offering.api_model_id: unknown
offering.attestation.baa: not_disclosed
offering.attestation.soc2: not_disclosed
offering.private_deployment: unknown
offering.router_slug: unknown
offering.speed.throughput: unknown
offering.speed.time_to_first_token: unknown

Evidence for Gemini 3.8 Flash

Benchmark	Version	Measurement	Unit	Published interval	Evidence date	Measurement conditions	Provenance
arena_elo_coding	Text Arena coding category, raw (not style-controlled)	1513.97	Arena score (Elo scale)	Unavailable	2026-09-13	Effort: Unavailable Subcategory: Unavailable Harness: Unavailable Measured by: independent_evaluator Sample size: Unavailable	Source
arena_sc_coding	text_style_control / coding, latest split, revision 1880dbebff5b	1534.96	Arena score (Elo scale)	Unavailable	2026-09-13	Effort: Unavailable Subcategory: Unavailable Harness: Unavailable Measured by: independent_evaluator Sample size: Unavailable	Source
arena_sc_industry_software_it_services	text_style_control / industry_software_and_it_services, latest split, revision 1880dbebff5b	1518.01	Arena score (Elo scale)	Unavailable	2026-09-13	Effort: Unavailable Subcategory: Unavailable Harness: Unavailable Measured by: independent_evaluator Sample size: Unavailable	Source
arena_webdev	webdev / overall, latest split, revision 1880dbebff5b	1583.75	Arena score (Elo scale)	Unavailable	2026-09-23	Effort: Unavailable Subcategory: Unavailable Harness: Unavailable Measured by: independent_evaluator Sample size: Unavailable	Source
cursorbench_4	CursorBench 4.0	39.6	percent	Unavailable	2026-09-30	Effort: high Subcategory: Unavailable Harness: Unavailable Measured by: benchmark_author Sample size: Unavailable	Source
deepswe_v1_1	DeepSWE v1.1, pass@1, mini-swe-agent	73.83	percent	Unavailable	2026-09-30	Effort: high Subcategory: Unavailable Harness: unregistered Measured by: benchmark_author Sample size: Unavailable	Source
frontiercode_v1_1	FrontierCode 1.1, main score (Mean@5)	41.2	percent	Unavailable	2026-09-30	Effort: medium Subcategory: Unavailable Harness: unregistered Measured by: benchmark_author Sample size: Unavailable	Source
terminal_bench_v4_0	Terminal-Bench 4.0	19.09	percent	Unavailable	2026-09-02	Effort: high Subcategory: Unavailable Harness: unregistered Measured by: benchmark_author Sample size: Unavailable	Source

Missing facts for Gemini 3.8 Flash

model.hardware_fit_indeterminate: unknown
model.languages: unknown
model.parameters_total: unknown
origin.base_lineage: not_disclosed
origin.weights_hosting: not_disclosed
offering.api_model_id: unknown
offering.attestation.baa: not_disclosed
offering.attestation.soc2: not_disclosed
offering.private_deployment: unknown
offering.router_slug: unknown
offering.speed.throughput: unknown
offering.speed.time_to_first_token: unknown

What this template teaches

Use Must for non-negotiable context and budget limits, then Prefer to trade coding strength against cost.

Decision dec_e714b968d27e687c50bbf4db on public snapshot snap_05a963d2477ac2fb.

Read the full dated job answer.

The live board uses current data. This link applies the template to its full lineup.

Apply this template on Decide

Human lookup is free on Decide. CLI, API, and MCP access requires a key. Access and pricing.

Use-case examples · Model comparisons · How we decide