Pixtral Large and Claude Haiku 5.5 have no benchmarks in common in this dataset, so their scores cannot be compared directly. The specification rows below still apply.
Pixtral Large is no longer available through its official API. API prices for this version are not shown.
Price basis: Listed rates vs listed rates. The price section below shows the applicable periods.
| Fact | Pixtral Large | Claude Haiku 5.5 |
|---|---|---|
| Context window | 128K tokens | 1M tokens |
| Input / 1M | — | $0.100 |
| Output / 1M | — | $0.500 |
| Blended (4:1) | — | $0.115 |
| Status | Retired | Available |
| Released | November 18, 2024 | October 7, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Published scores, with matching modes where available. Gaps show Pixtral Large relative to Claude Haiku 5.5. Reading the results
A dash means no result is available.
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
A blended cost needs a published input and output price on both sides, and one of these two does not have them yet.
Pixtral Large: Listed text rates; pricing tier not confirmed.
Claude Haiku 5.5: Standard pricing. context_length <= 100000 Prompt length tier; text and image inputs are token billed. context_length > 100000
| Price / 1M tokens | Pixtral Large | Claude Haiku 5.5 | Ratio |
|---|---|---|---|
| Input | — | $0.10 | — |
| Output | — | $0.50 | — |
| Cached input | — | $0.01 | — |
| Cache write | — | $0.125 | — |
| Blended | — | $0.115 | — |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
| Benchmark | Pixtral Large | Claude Haiku 5.5 |
|---|---|---|
| AA Decision Index v2.1 | Not reported | |
| AA Intelligence Index v5.0.1 | Not reported | 2 more settings |
| Agent Arena | Not reported | $0.0778 / task Median · Net improvement index (percentage points vs. average model): 0.42 Thinking High (With Tools + Internet) |
| Agent Arena Index | Not reported | $0.0944 / task Median · Agent Arena Index rating (index points): 1095 Thinking High (With Tools + Internet) |
| ARC-AGI-1 | Not reported | 2 more settings |
| ARC-AGI-2 | Not reported | 1 more settings |
| AutomationBench | Not reported | $0.03 / task Average · Pass Rate: 10.5 Thinking High (With Tools) · zapier-private-heldout 2 more settings$0.02 / task Average · Pass Rate: 8.5 Thinking Medium (With Tools) · zapier-private-heldout |
| Code Migration | Not reported | |
| CursorBench 4.0 | Not reported | $0.32 / task Average · Task score: 42.3 Thinking High (With Tools) · cursorbench-4-0-cursor-agent $0.08 / task Average · Task score: 30.9 Thinking Low (With Tools) · cursorbench-4-0-cursor-agent 2 more settings$0.17 / task Average · Task score: 36.9 Thinking Medium (With Tools) · cursorbench-4-0-cursor-agent $0.56 / task Average · Task score: 44.3 Extra-High (With Tools) · cursorbench-4-0-cursor-agent |
| EMB (Excel Modeling) | Not reported | |
| Finance Agent v2 | Not reported | |
| FrontierCode 1.1 | Not reported | $1.3284 / task Average · Weighted rubric score: 46.4 Max (With Tools) · frontiercode-1-1-main $0.256 / task Average · Weighted rubric score: 41.9 Thinking High (With Tools) · frontiercode-1-1-main $0.0596 / task Average · Weighted rubric score: 34.8 Thinking Low (With Tools) · frontiercode-1-1-main 2 more settings$0.13 / task Average · Weighted rubric score: 41.6 Thinking Medium (With Tools) · frontiercode-1-1-main $0.6297 / task Average · Weighted rubric score: 45.8 Extra-High (With Tools) · frontiercode-1-1-main |
| FrontierCode 2.0 | Not reported | $0.139 / task Average · Weighted rubric score: 18.6 Thinking High (With Tools + Internet) 2 more settings$0.097 / task Average · Weighted rubric score: 13.4 Thinking Medium (With Tools + Internet) |
| FrontierSWE v2 | Not reported | |
| GDPx | Not reported | |
| IOI (Vals v2) | Not reported | |
| Legal Research Bench | Not reported | |
| LiveBench 2.0 | Not reported | $0.6189 / task Average · Overall score (equal-weight mean of 7 suite scores, 0-100): 75.6 Max (task-specific tools) |
| MedCode | Not reported | |
| MedScribe | Not reported | |
| MysteryMechanism | Not reported | |
| ProofBench v1.1 (Lean 4) | Not reported | |
| Public Benefits Bench v1.1 | Not reported | |
| SAGE | Not reported | |
| Tax Agent Bench | Not reported | $1.1642 / task Average · Accuracy (%, rubric × citation quality): 31.9 Unspecified Reasoning (With Tools) |
| Terminal-Bench 2.1 | Not reported | |
| Terminal-Bench 4.0 | Not reported | $3.12 / task Average · Resolution rate (%): 36.4 Unspecified Reasoning (With Tools) · vals-mini-swe |
| Terminal-Bench 4.1 | Not reported | |
| Vals Index v2.2 | Not reported | |
| Vibe Code Bench 1-100 | Not reported | |
| Vibe Code Bench v1.1 | Not reported | |
| WeirdML v3 | Not reported | $2.3004 / task Average · Official score (0-1; higher is better): 0.12 Extra-High (With Tools) |
| Attribute | Pixtral Large | Claude Haiku 5.5 |
|---|---|---|
| Availability | Retired | Available |
| Provider | MistralAI | Anthropic |
| Model type | Multimodal model | Reasoning model |
| First release | November 18, 2024 | October 7, 2026 |
| Context window | 128K tokens | 1M tokens |
| Max output | — | 128K tokens |
| Total parameters | 124B | — |
| Active parameters | 124B | — |
| Architecture | Dense | Undisclosed |
| Documented capabilities | — | Reasoning |
| Knowledge cutoff | — | 2026-06 |
| Input modalities | Text, Image | Text, Image |
| Output modalities | Text | Text |
| Weights | Restricted weights | Closed / API only |
| Commercial use | Non-commercial only | Proprietary |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used Pixtral Large or Claude Haiku 5.5? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.