Kolibri 1

Released
2026-10-03
Last refreshed
2026-10-05
Status
Researched 45d ago
Open sourceCommercial use: permittedCodingRAGAgentsLong contextClassificationJSON / Tool useAgentCoding

Kolibri 1 is available now for coding, rag, and agents with open-source and 1M context; evaluate it while provider pricing coverage matures.

Aleph Alpha releases · 1 in the last 12 monthsChangelog →
Specifications
Family
Kolibri
Released
2026-10-03
Context
1M
Parameters
78B (3.46B activated)
Architecture
Mixture of Experts
Knowledge cutoff
2026-06
Specialization
general
Openness
Open source
License
Apache 2.0OSI-approvedPermitted
Weights
Available
Code
Unknown
Training
Multi-stage
Created by

Pioneering Trustworthy Explainable AI Solutions

Heidelberg, Germany
Founded 2019
Website
Pricing

No tracked provider pricing is available yet.

About

Kolibri (Kolibri 1, HF Aleph-Alpha/Kolibri-1) is Aleph Alpha's open-weight English–German mixture-of-experts reasoning model, released 3 October 2026 and trained from scratch in Germany. It has 78B total parameters (78,103,074,560) with 3.46B active per token: 50 layers, 384 routed experts plus 1 shared, top-6 sigmoid routing, and 4:1 sliding-window-to-full GQA attention. Native context is 262,144 tokens. Because RoPE is applied only in the sliding-window layers, Aleph Alpha validates up to 1,048,576 tokens via a max_position_embeddings override, and recommends at most 262,144 for serving efficiency and complex tasks. It is text-in, text-out with controllable reasoning effort (low/medium/high/none) and Hermes-style tool calling.

Providers

No active provider routes are tracked for this model yet.

Capabilities

ReasoningJSON / Tool useStructured Outputs

Benchmark peer barsfor Coding

Benchmark scores(11)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
84.3diamondObserved 2026-10-03—
80.0MMLU-Pro CoT (EN)Observed 2026-10-03—
96.9AIME 2025 (EN)Observed 2026-10-03—
96.0AIME 2026 (EN)Observed 2026-10-03—
85.9LiveCodeBench v6Observed 2026-10-03—
92.7HumanEval+Observed 2026-10-03—
66.4SWE-Bench Verified (Harbor)Observed 2026-10-03—
27.7TerminalBench 2.1 (Harbor)Observed 2026-10-03—
29.4BrowseCompObserved 2026-10-03—
61.4v4 (overall)Observed 2026-10-03—
94.7Tau2-Bench TelecomObserved 2026-10-03—

Migration checks

No linked migration route is available for this model yet.

API versions

Aleph-Alpha/Kolibri-1Aleph-Alpha/Kolibri-1-BF16Kolibri-1Kolibri 1Kolibri