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.
DeepSeek V4.1 Flash vs Gemini 3.7 Flash for Maths and reasoning on a budget, as of 2026-09-23
Find an active text model for maths and reasoning while keeping one task at or under $0.08.
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.
DeepSeek V4.1 Flash has a 44% 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 |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 0.648332 | [0.228226, 1.068438] | 16% | 0.0168 | deepseek / global / standard |
|
| Gemini 3.7 Flash | 0.712712 | [0.299602, 1.125822] | 21% | 0.045 | google-gemini-api / global / standard |
|
At most $0.08 a task; maths still ranked.
Requirements
model.class = text-generator: The answer must be generated as text.model.lifecycle = active: An active model is still supported by its lab or provider.offering.cost_per_task <= 0.08: The offering must stay within the per-task budget.
Preferences
maths: Prefer stronger maths among offerings inside the budget.-offering.cost_per_task: Prefer the cheaper task among offerings inside the budget.
Applied template spec
spec_version- 1
where- model.class = text-generator
- model.lifecycle = active
- offering.cost_per_task <= 0.08
optimizeweightsmaths- 0.5
-offering.cost_per_task- 0.5
Evidence for DeepSeek V4.1 Flash
| Benchmark | Version | Measurement | Unit | Published interval | Evidence date | Measurement conditions | Provenance |
|---|---|---|---|---|---|---|---|
| arxivmath | ArXivMath, MathArena Overall table | 53.28 | percent | Unavailable | 2026-09-30 |
| Source |
| brokenarxiv | BrokenArXiv, MathArena Overall table | 40.87 | percent | Unavailable | 2026-09-30 |
| Source |
| hle | HLE (Pass@1) | 36.8 | percent | Unavailable | 2026-09-10 |
| Source |
| hle_tools | HLE w/ tools (Pass@1) | 63.9 | percent | Unavailable | 2026-09-10 |
| Source |
Missing facts for DeepSeek V4.1 Flash
feature.batch: not_disclosedfeature.streaming: not_disclosedfeature.structured_output: not_disclosedlicence.commercial_use: not_disclosedlicence.fine_tuning: not_disclosedlicence.output_training: not_disclosedlicence.user_cap: not_disclosedmodel.context_window: not_disclosedmodel.input_modalities: not_disclosedmodel.languages: unknownmodel.max_output_tokens: not_disclosedmodel.output_modalities: not_disclosedmodel.release_date: not_disclosedorigin.base_lineage: not_disclosedorigin.lab_jurisdiction: not_disclosedorigin.weights_hosting: not_disclosedoffering.api_model_id: unknownoffering.attestation.baa: not_disclosedoffering.attestation.soc2: not_disclosedoffering.data.retention: not_disclosedoffering.data.trains_on_customer_data: not_disclosedoffering.data.zero_retention: not_disclosedoffering.price.batch_input: not_disclosedoffering.price.batch_output: not_disclosedoffering.private_deployment: unknownoffering.router_slug: unknownoffering.speed.throughput: unknownoffering.speed.time_to_first_token: unknown
Evidence for Gemini 3.7 Flash
| Benchmark | Version | Measurement | Unit | Published interval | Evidence date | Measurement conditions | Provenance |
|---|---|---|---|---|---|---|---|
| arena_sc_industry_mathematical | text_style_control / industry_mathematical, latest split, revision 1880dbebff5b | 1510.79 | Arena score (Elo scale) | Unavailable | 2026-09-13 |
| Source |
| arena_sc_math | text_style_control / math, latest split, revision 1880dbebff5b | 1521.51 | Arena score (Elo scale) | Unavailable | 2026-09-13 |
| Source |
| frontiermath_tiers_1_3_v2 | FrontierMath-Tiers-1-3-v2-Private (Epoch AI run) | 71.58 | percent | Unavailable | 2026-08-14 |
| Source |
Missing facts for Gemini 3.7 Flash
model.hardware_fit_indeterminate: unknownmodel.languages: unknownmodel.parameters_total: unknownorigin.base_lineage: not_disclosedorigin.weights_hosting: not_disclosedoffering.api_model_id: unknownoffering.attestation.baa: not_disclosedoffering.attestation.soc2: not_disclosedoffering.private_deployment: unknownoffering.router_slug: unknownoffering.speed.throughput: unknownoffering.speed.time_to_first_token: unknown
What this template teaches
The budget is a Must; inside it, cost and maths share the ranking equally.
Decision dec_4b2c9257cb14cd34c3c7d1c0 on public snapshot snap_745a6b4354bbc69a.
Read the full dated job answer.
The live board uses current data. This link applies the template to its full lineup.
Human lookup is free on Decide. CLI, API, and MCP access requires a key. Access and pricing.
Guides · Use-case examples · Model comparisons · How we decide