The Open-Source AI Stack
RSS
All models

Models · Compare

Mixtral 8x7B Instruct v0.1 vs Gemini 1.5 Pro

Rows highlighted in warm gray are where the models differ. Numbers carry their as-of date and primary source.

Specs

Field A: Mixtral 8x7B Instruct v0.1 B: Gemini 1.5 Pro
Released 2023-12-112024-02-15
Developer Mistral AIGoogle DeepMind
Openness OpenProprietary
License Apache-2.0Proprietary
OSI-approved yesno
Data released nono
Training code nono
Architecture moeunknown
Total params 46.7B
Active params 12.9B
Experts 8 (2 active)
Context window 33K2.1M
Attention gqaunknown
Position enc. ropeunknown
Pretraining tokens
Post-training sft, dporlhf
Training hardware
$/M input $0.00
$/M output $0.00
Output tok/sec 0

Benchmarks

Missing scores render as not reported; never inferred. Bold highlights the leader per benchmark.

General reasoning

MMLU-Pro 75.0 2026-05-21
GPQA-Diamond 58.9 2026-05-21

Code

LiveCodeBench 31.6 2026-05-21

Math

MATH 87.6 2026-05-21
AIME 2024 23.0 2026-05-21

Context · A

The first widely-used open-weights MoE, with 8 experts and 2 active per token. Quality matched dense 70B-class models at ~13B active parameter inference cost.

Context · B

Google's first long-context Gemini checkpoint, introduced with a 128K standard window and a 1M token preview tier. Google described the design as a mixture-of-experts that activates a subset of expert networks per input, and demonstrated 99% recall on needle-in-a-haystack across 1M tokens at launch. The context window was later extended to 2M tokens in private preview, announced May 14 2024.

Mixtral 8x7B Instruct v0.1 detail → · Gemini 1.5 Pro detail →