Skip to content
ModelCap

Head-to-head comparison

DeepSeek V3.1 Terminus vs K2 Horizon MoVA 36B A4B

DeepSeek V3.1 Terminus (DeepSeek) and K2 Horizon MoVA 36B A4B (IFM) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.

Snapshot as of 10 September 2026

As of 10 September 2026, DeepSeek V3.1 Terminus holds the stronger ModelCap Index position (#67 vs #70).

Which should you choose?

Choose DeepSeek V3.1 Terminus if…

  • you want the stronger overall ModelCap Index position — #67 against #70 (54.1 vs 53.1 points).
  • you want provider choice — 4 listed API providers against 0.

Choose K2 Horizon MoVA 36B A4B if…

  • you want the more recently listed model — K2 Horizon MoVA 36B A4B was listed 1 September 2026, DeepSeek V3.1 Terminus 22 September 2025.

DeepSeek V3.1 Terminus vs K2 Horizon MoVA 36B A4B: specs, pricing and context

Specification comparison of DeepSeek V3.1 Terminus and K2 Horizon MoVA 36B A4B
FieldDeepSeek V3.1 TerminusDeepSeekK2 Horizon MoVA 36B A4BIFM
ModelCap Index position#67#70
Index score54.153.1
EvidenceMeasuredEstimated
Input price / 1M tokens$0.27Unlisted
Output price / 1M tokens$1.00Unlisted
Context window164K tokens— tokens
Max output tokens33K
API providers listed40
Weight accessOpen weightsOpen weights
Input modalitiesTextText
First listed22 September 20251 September 2026
PublisherDeepSeekIFM

Evidence: 3 public benchmark observations across 3 boards · global-corpus-prior over 185 held-out anchors (64%); launch card against 4 resolved peers on 8 rows (36%); exceeds every named peer on 2 of 8 rows; optimism haircut 1.82 from cross-lab-probe; shrunk 0.7 up toward the measured corpus. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: DeepSeek V3.1 Terminus vs K2 Horizon MoVA 36B A4B

Public benchmark boards where DeepSeek V3.1 Terminus or K2 Horizon MoVA 36B A4B has a published result
BoardDeepSeek V3.1 TerminusK2 Horizon MoVA 36B A4BLeads
Arena codingArena (LMArena)14611438–1485ThinkingOnly one result
AA Intelligence IndexArtificial Analysis15.4intelligence-index:v4.3:reasoning-unspecifiedOnly one result
AA Terminal-Bench 2.1Artificial Analysis44.9%terminal-bench:2.1:terminus-2:e2b:pass-at-1:3-repeats:source-model="DeepSeek V3.1 Terminus":reasoning=trueOnly one result
AA τ²-Bench TelecomArtificial Analysis37.1%tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="DeepSeek V3.1 Terminus (Non-reasoning)":reasoning=falseOnly one result
AA Humanity's Last ExamArtificial Analysis8.7%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="DeepSeek V3.1 Terminus (Non-reasoning)":reasoning=falseOnly one result

Scores are the sources' own published figures for each model's best evaluated configuration; ModelCap never re-runs a benchmark.

Want a different pairing? Open the interactive comparison tool to swap either model for any current ranked language model.

DeepSeek V3.1 Terminus vs K2 Horizon MoVA 36B A4B: common questions

Is DeepSeek V3.1 Terminus better than K2 Horizon MoVA 36B A4B?

DeepSeek V3.1 Terminus ranks higher on the ModelCap Index as of 10 September 2026: #67 against #70. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.

Is DeepSeek V3.1 Terminus cheaper than K2 Horizon MoVA 36B A4B?

At least one of the two has no listed API price on ModelCap right now, so no price comparison is made.

Which has the bigger context window, DeepSeek V3.1 Terminus or K2 Horizon MoVA 36B A4B?

Both publish a 164K-token context window.

Which is better for coding, DeepSeek V3.1 Terminus or K2 Horizon MoVA 36B A4B?

The two models do not share a coding benchmark board on ModelCap yet, so no head-to-head coding score is published; the ModelCap Index position is the closest overall signal.

Are DeepSeek V3.1 Terminus and K2 Horizon MoVA 36B A4B open-weight models?

DeepSeek V3.1 Terminus: Open weights. K2 Horizon MoVA 36B A4B: Open weights. Open weights mean the checkpoint can be downloaded and self-hosted under its licence; API-only models are available solely through hosted endpoints.

Where can I run DeepSeek V3.1 Terminus and K2 Horizon MoVA 36B A4B?

ModelCap currently lists 4 API providers for DeepSeek V3.1 Terminus and 0 for K2 Horizon MoVA 36B A4B, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this DeepSeek V3.1 Terminus vs K2 Horizon MoVA 36B A4B comparison?

Every figure comes from the sealed ModelCap dataset published 10 September 2026; the page re-renders within a minute of each data refresh, and the ModelCap Index positions are the same ones shown on the live rankings.

Explore further