Mistral Medium 3.5 128B vs Grok 4.3
At a Glance
| Compare |  Mistral Medium 3.5 128BMistral AI | Grok 4.3xAI |
|---|---|---|
| Intelligence, Cost, and Efficiency | ||
| IntelligenceHigher is better · MM Intelligence v2.5 | UnrankedNot in the 46-model eligible cohort | #40 of 4616.6 score · 2/3 sources · provisional · missing ARC-AGI-2 · full-core range 11.1–44.4 |
| CostLower is better · Published-token output estimate | UnrankedNot in the 44-model eligible cohort | #7 of 44$0.028 per LiveBench case |
| EfficiencyHigher is better · MM Efficiency v1.5 | UnrankedNot in the 38-model eligible cohort | #33 of 3846.0 score · 2/3 sources · provisional · missing ARC-AGI-2 · full-core range 43.3–59.9 |
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | Not reported | $1.25Xai ↗ · Sep 3, 2026 |
| Output priceFrom · USD / 1M tokens | Not reported | $2.50Xai ↗ · Sep 3, 2026 |
| Context windowMaximum documented tokens | 262K | 1,000K |
| Model facts checked | Aug 28, 2026View model evidence → | Sep 3, 2026View model evidence → |
Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →
Available Benchmarks
| Benchmark | Mistral-Medium-3.5-128B | Grok 4.3 |
|---|---|---|
| LMArena Text Arenatext-2026-09-13-d25aabda0010 · arena_rating · leader | 1,420.58100% of row best · rating · mistral-medium-3.5; 95% CI [1414.04225396, 1427.11615611]; votes 10996; rank 104 | 1,397.7398% of row best · rating · grok-4.3; 95% CI [1394.01930088, 1401.44639527]; votes 66801; rank 145 |
| LMArena Vision Arenavision-2026-09-13-d25aabda0010 · arena_rating · statistical tie | 1,222.0599% of row best · rating · mistral-medium-3.5; 95% CI [1212.30064904, 1231.79518832]; votes 5090; rank 71 | 1,229.47100% of row best · rating · grok-4.3; 95% CI [1223.17337452, 1235.75913440]; votes 22688; rank 67 |
| Overall ResultCounted from the protocol-matched rows above · 1 tie | 1 benchmark winNo overall winner | 0 benchmark winsNo overall winner |
Third-party benchmark Only like-for-like primary-publisher results are shown; raw scores, relative scores, configuration, and token spend remain visible.
Side-by-Side Facts
| Field | Mistral-Medium-3.5-128B | Grok 4.3 |
|---|---|---|
| Developer | Mistral AI | xAI |
| Family | Mistral Medium 3 5 128b | Grok 4 |
| Model | Mistral-Medium-3.5-128B | Grok 4.3 |
| Version | Mistral-Medium-3.5-128B | Grok 4.3 |
| Lifecycle | active | active |
| Released | Unknown | 2026-06-17 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text, Image | Text, Image |
| Output modalities | Text | Text |
| Context window | 262K | 1,000K |
| Total parameters | 127.7B | Unknown |
| Active parameters | Unknown | Unknown |
| License | other | Unknown |
| Open weights | Yes | No |
| API available | Unknown | Yes |
| Self-hostable | Yes | No |
| Provider access | Unknown | Xai (Standard) |
| Capabilities | chat, generation, reasoning, tools | chat, generation, reasoning, structured_outputs, tools |
Mistral Medium 3.5 128B Capabilities
Grok 4.3 Capabilities
Related Comparisons
All image comparisons →| A | Pair | B | Context |
|---|---|---|---|
Mistral-Medium-3.5-128BMistral AI | vs |  GPT-6 AstraOpenAI | cross-developer peersimage, text |
Claude Fable 5.1Anthropic | vs | Mistral-Medium-3.5-128BMistral AI | cross-developer peersimage, text |
 Gemini 3.1 ProGoogle DeepMind | vs | Mistral-Medium-3.5-128BMistral AI | cross-developer peerstext |
 DeepSeek-V4.1-FlashDeepSeek | vs | Mistral-Medium-3.5-128BMistral AI | cross-developer peersimage, text |
Mistral-Medium-3.5-128BMistral AI | vs | Grok 4.6xAI | cross-developer peersimage, text |
Mistral-Medium-3.5-128BMistral AI | vs |  Qwen3.8-MaxQwen | cross-developer peersimage, text |
Mistral-Medium-3.5-128BMistral AI | vs |  Kimi-K3Moonshot AI | cross-developer peersimage, text |
 MiniMax-M3MiniMax | vs | Mistral-Medium-3.5-128BMistral AI | cross-developer peersimage, text |
Mistral-Medium-3.5-128BMistral AI | vs |  GLM-5.3Z.ai | cross-developer peerstext |
Mistral-Medium-3.5-128BMistral AI | vs |  Hy4 previewTencent | cross-developer peerstext |
Seed 2.1 ProByteDance Seed | vs | Mistral-Medium-3.5-128BMistral AI | cross-developer peersimage, text |
Mistral-Medium-3.5-128BMistral AI | vs | Mistral Large 3Mistral AI | family variantsimage, text |
Primary Evidence
Sources and Freshness
Questions
Mistral Medium 3.5 128B vs Grok 4.3 FAQs
Is Mistral Medium 3.5 128B or Grok 4.3 better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both Mistral Medium 3.5 128B and Grok 4.3, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, Mistral Medium 3.5 128B or Grok 4.3?+
Only Grok 4.3 has a directly sourced input price: $1.25 per million tokens. Only Grok 4.3 has a directly sourced output price: $2.50 per million tokens.
Which has a larger context window, Mistral Medium 3.5 128B or Grok 4.3?+
Grok 4.3 has the larger sourced context window. Mistral Medium 3.5 128B supports 262K and Grok 4.3 supports 1,000K.
Which performs better in benchmarks, Mistral Medium 3.5 128B or Grok 4.3?+
There is no overall benchmark winner: An overall winner requires at least two decisive benchmarks from at least two original publishers.
Can Mistral Medium 3.5 128B or Grok 4.3 be self-hosted?+
Mistral Medium 3.5 128B is the only model in this pair currently marked as self-hostable. Mistral Medium 3.5 128B is open weight; Grok 4.3 is not marked open weight.
Can Mistral Medium 3.5 128B and Grok 4.3 understand images?+
Mistral Medium 3.5 128B is documented with image input; Grok 4.3 is documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, Mistral Medium 3.5 128B or Grok 4.3?+
Neither has a larger sourced maximum output. Mistral Medium 3.5 128B is — and Grok 4.3 is —.
Do Mistral Medium 3.5 128B and Grok 4.3 support reasoning and tool use?+
Mistral Medium 3.5 128B: reasoning, tool calling, and image input. Grok 4.3: reasoning, tool calling, and image input. Feature support does not establish relative quality.
Which is available from more inference providers, Mistral Medium 3.5 128B or Grok 4.3?+
Mistral Medium 3.5 128B has 0 sourced provider routes; Grok 4.3 has 1, so Grok 4.3 has broader tracked availability.
Which offers better value, Mistral Medium 3.5 128B or Grok 4.3?+
There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.